Machine Learning
Posterior Flow Matching
Chenrui Ma, Xi Xiao, Lin Zhao et al. (+4 more)
Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state. This paper introduces Posterior Flow Matching (PFM), a general generative modeling framework that learns conditional velocity means and componentwise variances with a Gaussian posterior model. The same model evaluation supplies both a transport prediction and endpoint uncertainty, making posterior diagnostics available throughout generation. These learned moments support a mean-driven ordinary differential equation (ODE) and a posterior-driven
stochastic differential equation (SDE), whose local noise scales adapt to the predicted uncertainty. Across image, point-cloud, molecular, and action generation, PFM improves generation quality and provides endpoint-posterior readouts throughout generation.
Read the full abstract ▾
All authors Chenrui Ma, Xi Xiao, Lin Zhao, Xinru Jiang, Tianyang Wang, Yanning Shen, Ferdinando Fioretto
Machine Learning · Cross-listed from cs.CV
How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings
Mahmoud Mannes, Nikhil Maturi, Parva Mehta et al. (+2 more)
Positional
embeddings encode the spatial position of each image patch in a
Vision Transformer (ViT), allowing the model to distinguish different spatial arrangements of visual content. However, we know little about how the choice of
embedding shapes a
vision transformer's internal representation. In this work, we show that Absolute Positional
Embeddings (APE) and Rotary Positional
Embeddings (RoPE) encode spatial position through different internal mechanisms: APE stores position in explicit features, while RoPE builds it inside
attention and rebuilds it when it is withheld. Specifically, in APE models, sparse autoencoders recover causal row- and column-specific features, whereas interventions on RoPE reveal distinct rotary components that separately encode row and column information. Additionally, causal interventions selectively disabling RoPE's row or column rotations show that decodable row and column information can be independently removed and, once rotations are restored, partly reconstructed, in part by axis-specialized
attention heads. Both mechanisms are causally important for classification: permuting APE's positional features across patches reduces top-1 accuracy by 24–31 points, and ablating the rotations of RoPE's primary rebuilding head reduces it more than ablating those of any other head. Our findings show that the choice of positional encoding fundamentally changes how spatial information is organized and processed inside
Vision Transformers. More broadly, our work demonstrates how mechanistic analysis can reveal how models construct, reconstruct, and maintain structured representations, providing a basis for targeted interventions in
vision models.
Read the full abstract ▾
All authors Mahmoud Mannes, Nikhil Maturi, Parva Mehta, Jiwon Jeong, Aravind Singaram Kannappan
Machine Learning
Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents
Zixuan Xie, Chang Xu, Yuhua Jiang et al. (+1 more)
Self-evolving
agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only after costly evaluations, and aggregate scores may obscure distinctions between failures that require different repairs. We introduce predictive self-
evolution through an editable Improvement Dynamics Model (IDM). Before evaluation, the IDM predicts task-level outcomes of a proposed modification and guides an optional revision. After evaluation, past modifications and their observed outcomes are used to improve the IDM, allowing predictive knowledge to accumulate across generations. The system can thus improve how it solves tasks, proposes modifications, and predicts their effects. Building on HyperAgents, we evaluate this approach across
multilingual coding, paper review, robotics reward design, and Olympiad-level mathematical grading. Our approach outperforms HyperAgents across all four domains, with up to 46% higher average performance over generations. Gains also persist under matched
token budgets that include both
agent evolution and task evaluation, and extend to held-out tasks. Forecast accuracy improves as the IDM evolves, and the learned predictive knowledge transfers to improve
evolution in a new domain.
Read the full abstract ▾
All authors Zixuan Xie, Chang Xu, Yuhua Jiang, Li Zhao
Machine Learning
Fanxu Meng and Taosong Fang
Sparse
attention visits few keys, yet finding them can still require scoring every key with every indexer head. We introduce DoSA (Dots Sparse
Attention), a lossless method for making this computation conditional while preserving exact
token selection. Its central observation is that Top-K selection requires sufficient evidence to reject a candidate, not necessarily its full score. A seed set supplies a lower bound on the winning threshold. Nonnegative head projections and joint residual bounds upper-bound positive contributions, while activation-informed aggregation bounds the magnitude subtracted by negative heads. The certificate directs full scoring toward candidates that remain eligible; exact-score filtering further reduces writeback and selection work. We establish the certificate and its exact-selection conditions, and analyze how geometry and selection margins govern its effectiveness. Our GPU implementation accelerates the complete Indexer by up to 2.74 times over SGLang and 1.69 times over LiteTopK across English, Chinese, and code workloads. End-to-end evaluation on GLM-5.2 and DeepSeek-V3.2 achieves up to 1.94 times and 1.50 times time-to-first-
token speedups over the two baselines, respectively.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems
Chong Zhang, Qijie Shen, Haichao Zhang et al. (+3 more)
Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-based
agents generally function as surface imitators that generate realistic short-term responses but fail to capture the underlying user dynamics such as fatigue, affect, and shifting preferences. We propose PsyBer-
Agent, a psychology-inspired simulator that models these dynamics through its Psy-Engine. This engine represents each user with three evolving, model-defined latent states. To calibrate simulated behavior against real interaction logs, we align log-conditioned reference trajectories with simulator-generated latent-state trajectories via Unbalanced Gromov–Wasserstein optimal transport. This approach provides structured supervision for a lightweight policy without the computational burden of fine-tuning the backbone LLM. We also introduce WebSim and the PsyBer
Benchmark, which encompass
multimodal scenarios and seven recommender backbones. Our framework evaluates behavioral fidelity, latent-state consistency, robustness, and responses to social-cue perturbations. On the tested horizons, PsyBer-
Agent shows lower behavioral discrepancy than the
prompt-only simulators while maintaining stable performance under large-scale concurrent simulation for up to 5M queued simulation tasks under bounded concurrency. Code is available in the supplementary material and at: PsyBer-
Agent: https://anonymous.4open.science/r/CC66F/, WebSim Platform: https://anonymous.4open.science/r/D8EAX/.
Read the full abstract ▾
All authors Chong Zhang, Qijie Shen, Haichao Zhang, Can Wang, Xiaobo Jin, Jia Wang
Machine Learning
An Input-Dependent Readout Phase for Resonant Sequence Models
Shivesh Rane
Sequence models with a fixed-size state avoid the quadratic cost of
attention, but face a design choice. An input-dependent state transition gives content-dependent
memory at the cost of FFT-based training, while a fixed transition keeps the O(T log T) convolutional path but reads
memory the same way for every input. ResonatorLM, a recent model of the second kind, reads a bank of damped complex oscillators through a fixed learned phase per head. We make that readout phase a function of the current
token, which adds input dependence to the read only, keeps the convolution exact, and costs 0.2 percent more parameters. An analysis of the untrained bank shows that phase does encode elapsed time, but an ordinary
token falls below the background within 2-8 steps and no choice of damping extends linear reconstruction beyond about 16
tokens. In 6M-parameter character-level models on WikiText-2, the input-dependent phase matches the original at the training length and removes its failure beyond it: trained on 256
tokens and tested on 1024, perplexity falls from 12.81 to 3.76. We trace the failure to long-
memory heads that accumulate more history than training exposed them to. The learned phase tracks the current character rather than distance and does not improve
retrieval.
Read the full abstract ▾
Machine Learning
Kairos: Toward a Byte-Level Foundation Model for Every Modality
Fabien Furfaro
Small
language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear
attention and sliding-window
attention over shared projections (LiZAttention2), block-wise
Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) feed-forward layer and a multi-scale byte-level codec, trained with a uniform-noise denoising objective over one byte space shared by text, image, audio,
video,
lidar and control streams; this report asks whether the combination optimizes at all before asking whether it is useful. We give code-derived
algorithms for each component, including a cross-session recurrent-state
memory gate, then run convergence sanity checks: overfittinga single 440-byte sentence at 1–15M parameters, text only, with three seeds for codec and
attention choices and single-run sweeps for seven further factors. The two
attention variants tested at 3\,000 steps (LiZAttention2 and window
attention alone) reach a minimum loss near $10^{-3}$. After 600 steps, the mean minimum loss ranges from 0.018 (patch codec) to 0.354 (depthwise convolutional codec) with an identical ranking on three seeds. An apparent advantage of shared over separate
attention projections closes with more steps or more diverse data and reverses when the projections are frozen: it is a convergence-speed effect, not a capacity effect. These checks suggest that the implementation optimizes; they say nothing about generalization,
multimodal training or comparison with existing models, which a planned pretraining run is meant to address. The Discussion sizes a 200M-total/25M-active target analytically; none of its throughput figures is measured. Code is available at https://github.com/fabienfrfr/Kairos . Python package at https://pypi.org/project/kairos-fm/ .
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GT
Axiom Satisfiability of Linear Rewards in Alignment
Soumya Nasipuri, Sayak Ray Chowdhury and Sanjukta Roy
Learning from human preference data is the dominant route to aligning
language models with human values. In linear social choice, where rewards are linear in a fixed feature representation of
prompt-response pairs, Ge et al.[2024] show that fitting such a reward by minimizing any non-decreasing convex loss, including BTL, fails PO and PMC. Moreover, no rule that reads only the majority relation can satisfy PO once the output is required to be linearly induced. We ask what it costs to enforce these axioms anyway. To this end, we relax the linear model to allow per-candidate slack. We compute the relaxed linear reward with the smallest total slack that satisfies the axioms with a margin $\eta$, the minimum required difference between two reward values. Our solution satisfies the axioms under no assumptions about the voters or how comparisons were collected. We bound the optimal total slack by $O(1)$ when $\eta$ is at most $O(\frac{1}{m^2})$ for $m$ candidates. Furthermore, we exhibit an instance that forces this bound, concluding that the rate is tight up to constants. In practice, the no. of candidates far exceeds the feature dimension, and only a linear reward can be evaluated on unseen responses. We therefore introduce a new method that charges the linear part for each comparison it gets wrong. It simultaneously minimizes the total slack and the no. of violations, with a parameter $\lambda$ trading off between them. We show that the total slack is monotone but saturating in $\lambda$: raising it reduces the violations of the deployed linear reward and increases the slack, yet the slack stays below $(\eta+\Delta\sqrt{d})\lfloor m^2/4\rfloor$, where $\Delta$ and $d$ are the diameter and dimension of the features, respectively. Experiments on both synthetic and real-life preference data corroborate our theory and show that the linear reward output by our method beats linear BTL.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.ao-ph
Generalizable Neural Downscaling of Earth System Model Wind Fields via Continuous Dynamics Modeling
Chenxi Yu, Jianan Wei, Hanlin Kong et al. (+3 more)
Accurate high-resolution wind field simulations are critical for resolving fine-scale atmospheric dynamics, yet the simulation of wind fields in Earth System Models (ESMs) remains limited by coarse spatial resolution and systematic biases. To address this, data-driven down scaling techniques have been widely used to enhance coarse-resolution ESM outputs. However, existing methods are typically tied to fixed discretizations, limiting generalization across models with different native resolutions. Here we formulate global near-surface wind downscaling as an operator-learning problem on continuous atmospheric state fields and develop a downscaling neural operator that maps coarse-scale fields to fine-scale counterparts across heterogeneous discretizations. The operator learning-based neural downscaling framework outperforms dominant baselines, recovers fine-scale physical structures, and generalizes to previously unseen ESMs and future
climate scenarios without retraining, while preserving long-term wind projection trends. These findings establish a generalizable paradigm for high-resolution
climate downscaling across diverse simulation outputs and future scenarios.
Read the full abstract ▾
All authors Chenxi Yu, Jianan Wei, Hanlin Kong, Hao Sun, Bian He, Wenguan Wang
Machine Learning · Cross-listed from cs.RO
Learning Social Navigation from Internet Videos in the Policy State Space
Jiaming Wang, Duc Thang Nguyen, Jizhuo Chen et al. (+4 more)
Training robust social-
navigation policies requires simulators with diverse scene layouts, terrain, and human motion, but constructing such environments and specifying pedestrian behavior is costly. We propose an efficient pipeline that converts ordinary
monocular walking
videos directly into closed-loop social-
navigation training environments in the policy's state space. Our key observation is that local social
navigation primarily depends on two types of information: where the
robot can traverse and how nearby pedestrians move. We therefore represent the static scene as a metric traversability map, which can be rigidly transformed under counterfactual
robot motion, while directly replaying the pedestrian trajectories recovered from the
video over time. This abstraction allows us to define the forward dynamics directly in the policy's state space and efficiently simulate counterfactual
robot states without reconstructing or rendering photorealistic observations. The resulting policy achieves 81.2% success in the independent Arena
benchmark, compared with 75.0% for the strongest baseline, and succeeds in 19/20 real-
robot trials without policy fine-tuning. Project page: https://jiaming.im/VideoSocNav
Read the full abstract ▾
All authors Jiaming Wang, Duc Thang Nguyen, Jizhuo Chen, Volodymyr Shcherbyna, Diwen Liu, Zhengcheng Shen, Harold Soh
Machine Learning · Cross-listed from cs.CR
Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
Beining Xu, Peichun Hua and Yunming Xiao
Agentic
retrieval-augmented generation (RAG) interleaves
reasoning with repeated
retrieval, giving the retriever influence over both the evidence an
agent observes and its subsequent search decisions. We study retriever
backdoors that exploit this feedback loop and repurpose weak
backdoor purification to conceal their presence. An attacker supplies a compromised retriever checkpoint while leaving the search
agent and deployment corpus unchanged. Without corpus write access, the attacker can still suppress useful evidence, persistently retrieve a selected existing document, or steer the
agent toward prolonged search, inflating
retrieval, context, and latency cost. To conceal these behaviors from detection, we propose leveraging a controlled inject-and-remove cycle: deliberately inject a weaker
backdoor and then unlearn it. This process weakens detector-visible signatures and fools the
backdoor detectors with an illusion of purification while preserving the malicious
retrieval behavior. These findings expose a systematic vulnerability in RAG systems in which a weak defense becomes an attacker's concealment tool for a backdoored retriever, even when the underlying corpus remains trustworthy.
Read the full abstract ▾
Machine Learning
From Static Policies to Adaptive Priors in Offline Reinforcement Learning
Tianwei Ni, Vineet Jain, Akash Karthikeyan et al. (+1 more)
Offline reinforcement learning (RL) has traditionally focused on learning policies for direct deployment under conservative objectives, where uncertainty outside the offline
dataset is treated pessimistically to ensure robustness. We argue that this formulation becomes incomplete when an offline-trained policy is subsequently updated through online interaction, as increasingly occurs in modern intelligent systems through test-time adaptation and online fine-tuning. This position paper argues that, in such settings, the objective of offline RL should extend beyond immediate deployment and instead prioritize learning adaptive policy priors: policies that preserve the capacity to improve during subsequent interaction through
memory, exploration, and self-correction. We formalize this perspective as adaptive offline reinforcement learning (AORL), distinguish it from offline-to-online RL, and explain why adaptability becomes important under distributional shift, limited
dataset coverage, and changing test-time conditions. We further discuss
Bayesian offline RL as one principled direction for constructing adaptive policy priors by preserving epistemic uncertainty over plausible environments. Finally, we outline connections, open challenges, and research directions for treating offline RL as preparation for future experience rather than as a static deployment problem.
Read the full abstract ▾
All authors Tianwei Ni, Vineet Jain, Akash Karthikeyan, Pierre-Luc Bacon
Machine Learning · Cross-listed from q-bio.GN
BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models
Monireh Safari, Pablo Millan Arias, Scott C. Lowe et al. (+3 more)
Many DNA foundation models are pretrained by masking parts of a sequence and asking the model to reconstruct them. Standard masked pretraining exposes the encoder to special [MASK]
tokens that are absent at inference, creating a mismatch between training and downstream use. The role of an explicit global sequence representation such as a [CLS]
token and how it should be trained also remain poorly understood for DNA barcodes. We introduce BarcodeMAE+ and study model architecture, global [CLS] representation, and auxiliary pretraining objectives across arthropod COI (BIOSCAN-5M) and fungal ITS (UNITE+INSD) barcodes. Across both barcode regions, the encoder-decoder MAE-LM architecture outperforms its matched encoder-only counterpart in nearly all evaluated configurations, supporting MAE-LM as an effective architectural design for DNA barcode foundation models. A trained global [CLS] representation provides substantial additional gains: on BIOSCAN-5M, [CLS] accuracy increases from 47.53% without an auxiliary objective to 80.65% with cross-
entropy genus classification. The best auxiliary objective is region-dependent: cross-
entropy performs best on BIOSCAN-5M, whereas pairwise same-genus classification performs best on UNITE+INSD, reaching 73.19% on Yeast and 63.07% on Filamentous Fungi. BarcodeMAE+ outperforms published DNA foundation model baselines on BIOSCAN-5M and achieves the highest Yeast accuracy among the evaluated UNITE+INSD baselines using frozen encoder representations. Similarity-weighted softmax KNN voting further stabilizes accuracy as neighbourhood size increases. Overall, encoder-decoder masked pretraining and an explicitly trained global representation are strong design choices for DNA barcode foundation models, while the optimal objective for learning that representation depends on the biological domain.
Read the full abstract ▾
All authors Monireh Safari, Pablo Millan Arias, Scott C. Lowe, Lila Kari, Angel X. Chang, Graham W. Taylor
Machine Learning
Hybrid Ensemble Learning for EEG-Based Epileptic Seizure Forecasting
Mason Dana and Khandaker Mamun Ahmed
Epileptic seizure
forecasting aims to provide actionable warnings before seizure onset, yet patient-independent generalization and false-alarm control remain major challenges. We propose a calibrated hybrid ensemble for
EEG-based seizure
forecasting that combines five deep learning models and three classical machine learning models through a logistic regression stacking meta-learner. The proposed pipeline integrates signal preprocessing, handcrafted feature extraction, class-imbalance handling, probability calibration, and clinically motivated post-processing. We evaluate the framework on CHB-MIT using strict Leave-One-Patient-Out (LOPO) cross-validation, with threshold and post-processing parameters selected only on held-out meta data. On the filtered cohort, excluding patients with anomalous preictal rates below 1% or above 15%, the model achieves 74.2% seizure-level sensitivity at 1.24 false alarms per hour, with an average warning time of 16.9 minutes. A test-tuned oracle constrained to the target false-alarm budget achieves 60.9% sensitivity at 0.951 false alarms per hour, highlighting the importance of reporting sensitivity together with realized false-alarm rates. Our code is available at: https://github.com/DanaMason/IEEE-CARS-Hybrid-Ensemble-Learning-for-
EEG-Based-Epileptic-Seizure-
Forecasting
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses
Ziyang Xu, Haitian Zhong, Hao Zhou et al. (+5 more)
Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated execution of the same program, making specialization difficult to identify. We introduce a controlled evaluation that separates answer coverage, repeatable task advantages, and gains from pre-execution selection. On 386 MATH-500 tasks, we compare eight generated harnesses plus a baseline with nine byte-identical baseline copies, using three executions per member. Identical programs yield 2.16 percentage points of repeat-averaged oracle headroom. Generated programs exhibit substantially more repeatable score patterns, but these chiefly reveal persistent weaknesses: losses relative to the baseline persist across all three repeats on 100 tasks, while persistent wins occur on only one task and are sensitive to answer extraction. The frozen selector gains 0.00 percentage points, and both populations reach 98.70% oracle coverage at 27 harness executions. Stable complementarity remains unresolved at three repeats. Supporting BIRD traces locate failures in mechanism implementation, activation, and output validity. Together, these findings establish why coverage and repeatability alone cannot justify claims of useful specialization. They motivate an evaluation standard for harness diversity: task advantages should persist across executions, guide usable decisions, and improve on additional fixed-program executions under matched inference budgets.
Read the full abstract ▾
All authors Ziyang Xu, Haitian Zhong, Hao Zhou, Hao Qin, Chenhan Jin, Te Qi, Shengze Xu, Tieyong Zeng
Machine Learning
ReLOBGen: Replayable Limit Order Book Message Generation
Junoh Kang, Kiseop Lee and Bohyung Han
We propose ReLOBGen, a method for generating limit order book (LOB) messages that are replayable by construction. Replayability is required for closed-loop
market simulation, yet existing LOB message generators may produce non-replayable raw messages, i.e., messages inconsistent with the current
market state. These generators therefore rely on post-hoc correction or rejection followed by resampling, which may alter the replayed message distribution or increase inference cost. ReLOBGen instead ensures replayability during generation: it selects the referenced order from the resting orders in the current LOB and then generates the remaining message fields to be consistent with that order and the
market state. For realistic reference selection, ReLOBGen samples from a learned distribution over eligible resting orders, efficiently computed from cached order representations and a context-dependent query. It then enforces the consistency of the remaining fields by masking out invalid
tokens. Together, these components enable efficient generation of realistic messages without post-hoc correction or resampling. In 500-message rollouts, ReLOBGen achieves 100% replayability, improves
market realism, particularly for top-of-book statistics and the relative prices of LOB messages, and provides a $2.7\text{-}3.6\times$ speedup per replayed message over the LOBS5 baseline.
Read the full abstract ▾
Machine Learning
What Must a World Model Distinguish for Planning?
Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu et al. (+2 more)
World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate prediction. We formalize this gap through a hierarchy of mechanism, response, and decision sufficiency. Given a candidate set, the planning query determines which physical variations matter and how precisely they must be preserved: coarse decisions can discard much of the information needed for prediction, whereas fine decisions may require nearly the same resolution. In practice, planners often adaptively search to construct candidates, and information unnecessary for final selection may still be needed to discover good candidates. What a world model must preserve therefore depends on the query, the candidate set, and the planner. We study these effects in a collision system, nonlinear dynamics, and robotic planning. These varying requirements raise a design question: where should query information enter the planning system? A model that jointly generates actions and outcomes conditioned on the query achieves lower regret than an action-conditioned world model on seen objectives, but this advantage largely disappears when generalizing to unseen objectives. Motivated by this, we propose a modular design in which the query determines where to look and an action-conditioned model predicts what will happen, allowing the same predictions to be reused across objectives.
Read the full abstract ▾
All authors Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu, Yifan Li, Pan Li
Machine Learning
Łukasiewicz Neural Networks Extended: Residual Architectures and Crystallization Strategies for Interpretable Rule Extraction
Carlos Leandro
A feed-forward neural network whose weights are integers and whose activation is the truncated identity implements,
neuron by
neuron, the connectives of Łukasiewicz many-valued logic. This exact correspondence — established theoretically by Castro and Trillas and developed into a training
algorithm by Leandro — enables symbolic knowledge extraction: training produces not a black-box model but a logical formula. Two obstacles have limited the approach to shallow architectures and small
datasets: crystallization (forcing weights to integers) succeeds only probabilistically under the original Levenberg–Marquardt training scheme, and the theoretical guarantees break down as networks grow deeper. This paper addresses both obstacles. First, we prove that residual connections (skip connections of the kind used in ResNets) extend Łukasiewicz neural networks to arbitrary depth while preserving the symbolic correspondence at merge
neurons by construction: merge
neurons in a Łukasiewicz residual block automatically satisfy the
neuron-classification proposition, regardless of the inner layer weights; inner-layer
neurons are trained toward representability by the crystallization strategy. Second, we analyse three crystallization strategies — Levenberg–Marquardt (corrected), straight-through estimation (STE), and proximal regularization — characterizing their theoretical guarantees, failure modes, and interpretability trade-offs.
Read the full abstract ▾
Machine Learning
Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors
Zhongxuan Liu, Yue Kang and Thomas C. M. Lee
Low-rank
matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommodate unknown links without directly exploiting
matrix or tensor rank. We address this gap by studying
stochastic matrix and tensor bandits with an unknown shared Lipschitz link and a low-rank index parameter under known regular candidate distributions and finite-variance noise. For monotone links, T-ESTOR combines robust, rank-adaptive Stein estimation with epoch-based greedy selection. Under exact selected-score access and a uniformly positive selected-design Stein signal, it achieves square-root regret with dimension dependence determined by the low-rank structure. For every admissible design, the monotone lower bound matches the rank, dimension, and horizon dependence up to logarithmic factors at large horizons, for fixed menu size and model/design constants. For nonmonotone links under a nonzero base-law Stein signal, T-BSTOR combines structured estimation with robust bin-based learning and attains the optimal $\widetilde{O}(T^{2/3})$ horizon rate for fixed dimensions, menu size, and model/design constants. Synthetic and CCLE-based experiments illustrate the benefits of structured estimation relative to vectorized and competing single-index baseline methods.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Decentralized Optimization with Cross-Coupled Mixed Affine Constraints
Ewsey Obzherin, Ilya Khomchenko, Natalia Shelegeda et al. (+4 more)
We study decentralized optimization with cross-coupled mixed affine constraints, where local and shared variables interact through two affine channels. We show that the intrinsic difficulty of combining separately well-conditioned channels is governed by their Friedrichs angle. This geometry induces a cross-coupling factor that cannot be removed by channelwise preconditioning and governs the additional affine-oracle and communication complexity. We develop an accelerated decentralized method with matching minimax guarantees in the smooth strongly convex regime and extend the framework to smooth and nonsmooth convex objectives. Experiments confirm the predicted dependence on cross-channel geometry and network conditioning.
Read the full abstract ▾
All authors Ewsey Obzherin, Ilya Khomchenko, Natalia Shelegeda, Nhat Trung Nguyen, Demyan Yarmoshik, Alexander Rogozin, Alexander Gasnikov
Machine Learning
Relative Generalization Invariance of LLM Pretraining
Fengzhuo Zhang, Shuche Wang, Shenggui Li et al. (+7 more)
Large
Language Model (LLM) pretraining performance is jointly shaped by three components of the training triplet: the optimizer, model architecture, and training data stream. However, how these components influence performance in distinct ways remains unclear. We take a first step toward isolating their effects by studying relative generalization. We introduce Relative Generalization Invariance (RGI), the invariance of the validation-loss difference between any two
tokens across models. We show that RGI approximately holds across a wide range of optimizers and moderate architectural variations, suggesting that these choices induce an approximately uniform shift in
token-wise losses. In contrast, changing the training data stream can substantially alter relative generalization. We further show that RGI cannot be explained by the neural tangent kernel or mean-field regimes alone and prove that it can emerge in an overparameterized quadratic model. Overall, our work identifies RGI as a new phenomenon in LLM pretraining that helps distinguish the effects of optimizers and architectures from those of training data.
Read the full abstract ▾
All authors Fengzhuo Zhang, Shuche Wang, Shenggui Li, Tianyu Ruan, Jianliang He, Ivor Tsang, Tianyu Pang, Chao Du, Tianwei Zhang, Zhuoran Yang
Machine Learning
Saturation-Insensitive Dueling Bandits with General Function Approximation
Chenggong Zhang, Xuheng Li, Qiwei Di et al. (+2 more)
We study contextual dueling bandits with general function approximation under the Bradley-Terry-Luce (BTL) preference model. A key challenge in this setting is the saturation of the preference model: when the current reward model can already distinguish two actions with high confidence, the resulting preference feedback becomes weakly informative, making it difficult to further improve reward estimation. Consequently, existing sample-complexity analyses often depend on the inverse-derivative factor $1 / \sigma'[\Delta_{r^\ast}]$ which can be prohibitively large when the link function $\sigma$ saturates for large reward gaps $\Delta_{r^\ast}$. To address this issue, we introduce `SI-CDB`, an
algorithm that selects opponent arms using a carefully designed heuristic for arm selection. This design enables saturation-insensitive reward learning and recovers the near-optimal dependence for linear reward classes, eliminating the unfavorable $1/\sigma'(\cdot)$ factor. The core of our analysis is a localized Eluder dimension framework tailored to dueling bandits with general function approximation. Our theoretical results also explain why two-arm regret analysis is crucial for improving single-arm performance in dueling bandits.
Read the full abstract ▾
All authors Chenggong Zhang, Xuheng Li, Qiwei Di, Weitong Zhang, Quanquan Gu
Machine Learning · Cross-listed from cs.RO
CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning
Shivam Aarya, Zhang Xi-Jia, Chengyue Huang et al. (+6 more)
Robot learning has largely relied on human-teleoperated demonstrations to acquire effective learnable behaviors. However, human-operated data collection processes can be unintuitive, difficult to scale, and inherently asynchronous. We explore an alternative: distilling physical behavior from general-purpose
multimodal foundation models into deployable
robot policies by using the foundation model itself as an autonomous demonstrator. While sufficiently capable models can generate successful zero-shot manipulation trajectories, repeatedly invoking them during physical execution is slow and expensive, limiting their utility as scalable data generators. As a solution, we introduce CAPEX, an experience-conditioned demonstration collection framework that uses execution experience from previous attempts to adapt how frequently the foundation model must observe, reason, and replan. We evaluate across RoboCasa tasks and on physical Franka and bimanual YAM-arm platforms, measuring task success, model calls,
token usage, collection time, and cost. We further train
Diffusion Policy and ACT on matched sets of human-teleoperated and foundation-model-generated demonstrations to evaluate the downstream learning value of autonomously collected data. We find that CAPEX increases the number of successful demonstrations by 4.3x while reducing the cost per successful demonstration by 80%. Policies trained on CAPEX-generated data approach the performance of those trained on matched human demonstrations; with longer training, this gap largely closes for policies trained from scratch. These results suggest that foundation models can serve as scalable sources of reusable
robot experience. Project page: https://capex-paper.github.io/
Read the full abstract ▾
All authors Shivam Aarya, Zhang Xi-Jia, Chengyue Huang, Junhyun Kim, Huishu Xue, Hrishit Leen, Roman Yakunin, Animesh Garg, Zsolt Kira
Machine Learning
What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use
Yixiao Chen, Ke Cheng, Jiangtao Guan et al. (+5 more)
What should data teach a
language model at a particular point in training? A
circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B
tokens. Availability counterfactuals then distinguish writing content from invoking available
memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early
circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.
Read the full abstract ▾
All authors Yixiao Chen, Ke Cheng, Jiangtao Guan, Shuo Huang, Yue Liu, Jun Zhang, Yuhong Liu, Jie Jiang
Machine Learning
Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
Haoming Chen, Nicolas Zilberstein, Santiago Paternain et al. (+1 more)
Graph reconstruction from partial observations often comes with structural side information, such as degree bounds, triangle counts, or an edge-density band. Prior-Informed Flow Matching (PIFM) reconstructs graphs by transporting a local prior toward the graph distribution, but it provides no mechanism to incorporate this side information. We put forth Constrained Primal-Dual PIFM (CPD-PIFM), which augments the sampler with Lagrange multipliers that evolve along each trajectory. The multipliers respond to constraint violations at a predicted endpoint and guide subsequent sampling steps without retraining. We prove that the sampler inherits PIFM's permutation equivariance and bound its expected terminal slack by a term that decays as the inverse square root of the number of steps, plus two approximation terms. On three link-prediction
benchmarks and nine combinations of
datasets and constraints, CPD-PIFM raises feasibility by 11-26 percentage points and remains competitive with fixed guidance without selecting a separate multiplier for each constraint.
Read the full abstract ▾
All authors Haoming Chen, Nicolas Zilberstein, Santiago Paternain, Santiago Segarra
Machine Learning
Adaptive Ensemble Selection for Noisy Labels on Tabular Data
Faizaan Ali, Inwon Kang and Oshani Seneviratne
Incorrect or corrupted labels in tabular
datasets can significantly degrade supervised learning performance, particularly when mislabeling is subtle and not easily detectable from feature space alone. In the context of automated or AI-augmented data science workflows, robust detection of such label noise is critical for building reliable models. We propose a data-centric
reasoning module for AI data science systems that automatically diagnoses
dataset quality and selects appropriate cleaning strategies. Given a
dataset, a meta-model predicts weights over a diverse set of detectors, including confidence-based, neighborhood-based, and distributional methods. Across
benchmark datasets with controlled noise, our approach achieves performance comparable to a Confident Learning baseline on average, with
dataset-dependent gains and losses, particularly in heterogeneous regimes. We further show that detector effectiveness is systematically linked to
dataset properties. These results demonstrate the value of descriptor-driven, data-centric ensembling as a component of AI-assisted data-science pipelines for robust
dataset assessment and model reliability.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Distributed Hydrological Modeling in the Feature Space
Mohamad Hakam Shams Eddin, Maria Luisa Taccari, Yikui Zhang et al. (+3 more)
Accurate
forecasting of river discharge and floods is very challenging. River dynamics are affected by storage, meteorological forcing, and flow propagation at different spatial and temporal scales.
Forecasting thus requires a framework that considers the upstream-to-downstream flow through river networks across grid
cells and catchments. This modeling is known in hydrology as distributed modeling and routing. Existing deep learning approaches either ignore this
topology, operate on lumped catchments, or route predicted physical quantities through a separate graph or physical routing model. We instead introduce feature-space routing: a
topology-aware state-space operator embedded directly in the
forecasting dynamics. At every forecast step, the operator gathers latent states from upstream grid
cells and causally updates the downstream state according to the known river network. This preserves the physical connectivity of the river system while allowing the propagated state itself to be learned end-to-end and allows the model to predict river discharge considering both local dynamics and neighboring upstream contributions. To address uncertainty and provide probabilistic forecasts, we minimize the fair continuous ranked probability score (fCRPS) as a training objective. Our experiments on the European Flood Awareness System (EFAS) and observational data for river discharge
forecasting demonstrate that encoding the physical structure of river networks explicitly in the feature space substantially improves the
forecasting skill, particularly in an ungauged setting. Our approach achieves state-of-the-art results on both reanalysis and observational data and is able to forecast maps of river discharge at 1 arcminute and 6-hourly resolution up to 10 days lead time.
Read the full abstract ▾
All authors Mohamad Hakam Shams Eddin, Maria Luisa Taccari, Yikui Zhang, Shijie Jiang, Juergen Gall, Markus Reichstein
Machine Learning
Self-Confirming Superposition Traps in Reinforcement Learning
Dai Shi, Andi Han, Feng Chen et al. (+3 more)
Reinforcement learning (RL) trains representations on data selected by the
agent's policy, which then uses the resulting returns to guide its next choices. We show that this loop can sustain a lower-return policy even when representation fitting is globally optimal on those data. In a self-confirming superposition trap, every optimal code assigns overlapping directions to features that rarely occur together under the current policy. An alternative action brings them together, causing interference that lowers its return and reinforces avoidance, although refitting to that action would yield more return at the same capacity. We characterize the dimensions admitting a trap in a tied two-step model and show separately that equal feature frequencies, continued visitation, and independent controller learning need not prevent it. Because fitting weights errors by visitation, an avoided action can lose its return advantage at little cost to the objective. In a finite-action model, we bound this distortion and derive a replay condition: sufficient training weight on the best separately adapted action preserves its ranking despite residual error. Neural PPO experiments show how the feedback develops during learning:
agents initialized toward different actions develop different interference patterns, opposite mean return rankings, and different final policies at the same capacity. We therefore test whether retaining access to neglected states can improve control. Keeping these states in training reduces measured interference and improves sequential return, with gains even when the encoder is frozen. Related interventions on state access, replay weights, and feature overlap improve control on MiniGrid and DMControl. For
agents that learn through a world model, protected fitting improves DreamerV3–Crafter's cumulative training scores at unchanged capacity.
Read the full abstract ▾
All authors Dai Shi, Andi Han, Feng Chen, Yiqun Duan, Junbin Gao, José Miguel Hernández-Lobato
Machine Learning
Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise
Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh et al. (+5 more)
Gradient clipping is widely used to stabilize training, but it need not improve the statistical accuracy of averaged SGD, even under heavy-tailed noise. We derive a finite-sample comparison of clipped and unclipped Polyak-Ruppert averaged SGD under finite conditional $p$-th moments, $p\ge2$. Our main result gives explicit accuracy and confidence conditions under which, for $p>2$, the Gaussian term dominates the unclipped deviation bound, so clipping need not improve its leading order. By balancing clipping bias and concentration, we obtain a bound in which the heavy-tail correction depends logarithmically rather than polynomially on the inverse failure probability. At $p=2$, this improves the confidence dependence of the leading bound. We establish sharpness of the unclipped heavy-tail term through an exact one-dimensional quadratic recursion and extend the comparison to projected convex SGD. We also prove concrete costs of clipping: every fixed finite threshold increases asymptotic variance on a scalar Gaussian quadratic, while whole-gradient clipping can shift the limiting point under asymmetric noise.
Read the full abstract ▾
All authors Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh, Artem Agafonov, Mohammad Alkousa, Yuriy Dorn, Vladislav Matyukhin, Alexander Gasnikov
Machine Learning
Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents
Ritul Satish, Prasoon Sinha, Akiho Kawada et al. (+1 more)
As LLM
agents tackle longer tasks, they increasingly compress growing histories of
reasoning, actions, and tool outputs. Compression can reduce
token use, but it also changes the information available for later decisions. Existing agentic harnesses bundle decisions about what to compress, when to compress, and how much to remove into fixed policies. A systematic characterization is needed to disentangle these decisions and reveal how each affects task success and execution cost. We systematically vary these decisions across three open-weight models on SWE-bench Verified and Terminal-Bench 1.0. Across nearly 35,000
agent runs, we measure task success,
token use, end-to-end latency, and estimated cost. We find that fewer
tokens need not mean faster or cheaper execution: on Terminal-Bench with Qwen, policies using roughly one-third as many
tokens can take 20-80% longer than the uncompressed
agent. Policies with similar overall success can solve different tasks, while the same policy can perform quite differently across models. Our results motivate evaluating compression by its effects on
agent execution and tailoring policies to the task, model, and workload.
Read the full abstract ▾
All authors Ritul Satish, Prasoon Sinha, Akiho Kawada, Neeraja J. Yadwadkar