Machine Learning
Online Learning in MDPs with Partially Adversarial Transitions and Losses
Ofir Schlisselberg, Tal Lancewicki and Yishay Mansour
We study reinforcement learning in MDPs whose transition function is
stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce conditioned occupancy measures, which remain stable across episodes even with
adversarial transitions, and use them to design two
algorithms. The first handles arbitrary
adversarial steps and achieves regret $\tilde{O}(H S^{\Lambda}\sqrt{K S A^{\Lambda+1}})$, where $K$ is the number of episodes, $S$ is the number of state, $A$ is the number of actions and $H$ is the episode's horizon. The second, assuming the
adversarial steps are consecutive, improves the dependence on $S$ to $\tilde{O}(H\sqrt{K S^{3} A^{\Lambda+1}})$. We further give a $K^{2/3}$-regret reduction that removes the need to know which steps are the $\Lambda$
adversarial steps. We also characterize the regret of
adversarial MDPs in the fully
adversarial setting ($\Lambda=H-1$) both for full-information and bandit feedback, and provide almost matching upper and lower bounds (slightly strengthen existing lower bounds, and clarify how different feedback structures affect the hardness of learning).
Read the full abstract ▾
Machine Learning
Scalable and Reliable State-Aware Inference of High-Impact N-k Contingencies
Lihao Mai, Chenhan Xiao and Yang Weng
Increasing penetration of inverter-based resources, flexible loads, and rapidly changing operating conditions make higher-order $N\!-\!k$ contingency assessment increasingly important but computationally prohibitive. Exhaustive evaluation of all outage combinations using AC power-flow or ACOPF is infeasible in routine operation. This fact forces operators to rely on heuristic screening methods whose ability to consistently retain all critical contingencies is not formally established. This paper proposes a scalable, state-aware contingency inference framework designed to directly generate high-impact $N\!-\!k$ outage scenarios without enumerating the combinatorial contingency space. The framework employs a conditional
diffusion model to produce candidate contingencies tailored to the current operating state, while a
topology-aware graph neural network trained only on base and $N\!-\!1$ cases efficiently constructs high-risk training samples offline. Finally, the framework is developed to provide controllable coverage guarantees for severe contingencies, allowing operators to explicitly manage the risk of missing critical events under limited AC power-flow evaluation budgets. Experiments on IEEE
benchmark systems show that, for a given evaluation budget, the proposed approach consistently evaluates higher-severity contingencies than uniform sampling. This allows critical outages to be identified more reliably with reduced computational effort.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model
Shinsaku Sakaue and Yuichi Yoshida
We study online learning in the random-order model, where the multiset of loss functions is chosen adversarially but revealed in a uniformly random order. By extending the batch-to-online transformation of Dong and Yoshida (2023), we show that if an offline
algorithm enjoys a $(1+\varepsilon)$-approximation guarantee, an average sensitivity bound controlled by a function $\varphi(\varepsilon)$, and stability with respect to $\varepsilon$, then we can obtain a small-loss regret bound typically of order $\tilde O(\varphi^{\star}(\mathrm{OPT}_T))$, where $\varphi^{\star}$ is the concave conjugate of $\varphi$, $\mathrm{OPT}_T$ is the offline optimum over $T$ rounds, and $\tilde O$ hides polylogarithmic factors in $T$. Our result refines their original $(1+\varepsilon)$-approximate regret guarantee and applies to a broad class of problems, including online $k$-means clustering and online low-rank approximation. We further apply our approach to online submodular function minimization using $(1\pm\varepsilon)$-cut sparsifiers of submodular hypergraphs, obtaining a small-loss regret bound of $\tilde O(n^3 + n^{3/4}\mathrm{OPT}_T^{3/4})$, where $n$ is the ground-set size; we also demonstrate its applicability to online $\ell_1$ regression. Our work sheds light on the power of sparsification and related algorithmic techniques in achieving small-loss regret bounds in the random-order model, without requiring structural assumptions on loss functions, such as linearity or smoothness.
Read the full abstract ▾
Machine Learning
Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits
Hao Qin and Chicheng Zhang
We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual bandits with large action spaces with $O(\log T)$ calls to an offline regression oracle over $T$ rounds, and makes $O(\log\log T)$ calls when $T$ is known. The design of OE2D
algorithm generalizes Falcon~\citep{simchi2022bypassing} and its linear reward version~\citep[][Section 4]{xu2020upper} in that it finds an action distribution that we term “exploitative F-design” that simultaneously guarantees low regret and good coverage, striking a balance between exploration and exploitation. Central to our regret analysis is a new complexity measure, the Decision-Offline Estimation Coefficient (DOEC), which we show is small in many settings, including bounded Eluder dimension per-context and the smoothed regret setting. We also establish a relationship between DOEC and Decision Estimation Coefficient (DEC)~\citep{foster2021statistical}, bridging the design principles of offline- and online-oracle efficient contextual bandit
algorithms for the first time.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GT
Enhancing Affine Maximizer Auctions with Correlation-Aware Payment
Haoran Sun, Xuanzhi Xia, Xu Chu et al. (+1 more)
Affine Maximizer Auctions (AMAs), a generalized mechanism family from VCG, are widely used in automated mechanism design due to their inherent dominant-strategy incentive compatibility (DSIC) and individual rationality (IR). However, as the payment form is fixed, AMA's expressiveness is restricted, especially in distributions where bidders' valuations are correlated. In this paper, we propose Correlation-Aware AMA (CA-AMA), a novel framework that augments AMA with a new correlation-aware payment. We show that any CA-AMA preserves the DSIC property and formalize finding optimal CA-AMA as a constraint optimization problem subject to the IR constraint. Then, we theoretically characterize scenarios where classic AMAs can perform arbitrarily poorly compared to the optimal revenue, while the CA-AMA can reach the optimal revenue. For optimizing CA-AMA, we design a practical two-stage training
algorithm. We derive that the target function's continuity and the generalization bound on the degree of deviation from strict IR. Finally, extensive experiments showcase that our
algorithm can find an approximate optimal CA-AMA in various distributions with improved revenue and a low degree of violation of IR.
Read the full abstract ▾
All authors Haoran Sun, Xuanzhi Xia, Xu Chu, Xiaotie Deng
Machine Learning · Cross-listed from cs.IR
The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training
Xincan Feng, Noriki Nishida, Yusuke Sakai et al. (+1 more)
Synthetic query generation has become essential for training dense retrievers, yet prior methods generate one query per document, focusing solely on query quality. We are the first to systematically study multi-query synthesis and discover a quality-diversity trade-off: high-quality queries benefit in-domain tasks, while diverse queries benefit out-of-domain (OOD) generalization. Through controlled experiments on 4
benchmark types across Contriever, RetroMAE, and Qwen3-
Embedding, we find that diversity benefit strongly correlates with query complexity (r$\geq$0.95, p<0.05), approximated by content words (CW). We formalize this as the Complexity-Diversity Principle (CDP): query complexity determines optimal diversity. Based on CDP, we propose complexity-aware training: multi-query synthesis for high-complexity tasks and CW-weighted training for existing data. Both strategies improve OOD performance on
reasoning-intensive
benchmarks, with compounded gains when combined.
Read the full abstract ▾
All authors Xincan Feng, Noriki Nishida, Yusuke Sakai, Yuji Matsumoto
Machine Learning · Cross-listed from cs.CV
A Scoping Review of Deep Learning for Urban Visual Pollution and Proposal of a Real-Time Monitoring Framework with a Visual Pollution Index
Mohammad Masudur Rahman, Md. Rashedur Rahman, Ashraful Islam et al. (+2 more)
Urban Visual Pollution (UVP) has emerged as a critical concern, yet research on automatic detection and application remains fragmented. This scoping review maps the existing deep learning-based approaches for detecting, classifying, and designing a comprehensive application framework for visual pollution management. Following the PRISMA-ScR guidelines, seven academic databases (Scopus, Web of Science, IEEE Xplore, ACM DL, ScienceDirect, SpringerNatureLink, and Wiley) were systematically searched and reviewed, and 26 articles were found. Most research focuses on specific pollutant categories and employs variations of YOLO, Faster R-CNN, and EfficientDet architectures. Although several
datasets exist, they are limited to specific areas and lack standardized taxonomies. Few studies integrate detection into real-time application systems, yet they tend to be geographically skewed. We proposed a framework for monitoring visual pollution that integrates a visual pollution index to assess the severity of visual pollution for a certain area. This review highlights the need for a unified UVP management system that incorporates pollutant taxonomy, a cross-city
benchmark dataset, a generalized deep learning model, and an assessment index that supports sustainable urban aesthetics and enhances the well-being of urban dwellers.
Read the full abstract ▾
All authors Mohammad Masudur Rahman, Md. Rashedur Rahman, Ashraful Islam, Saadia B Alam, M Ashraful Amin
Machine Learning
Diffusion-Guided Pretraining for Brain Graph Foundation Models
Xinxu Wei, Rong Zhou, Lifang He et al. (+1 more)
With the growing interest in foundation models for
brain signals, graph-based pretraining has emerged as a promising paradigm for learning transferable representations from connectome data. However, existing contrastive and masked autoencoder methods typically rely on naive random dropping or masking for augmentation, which is ill-suited for
brain graphs and hypergraphs as it disrupts semantically meaningful connectivity patterns. Moreover, commonly used graph-level readout and reconstruction schemes fail to capture global structural information, limiting the robustness of learned representations. In this work, we propose a unified
diffusion-based pretraining framework that addresses both limitations. First,
diffusion is designed to guide structure-aware dropping and masking strategies, preserving
brain graph semantics while maintaining effective pretraining diversity. Second,
diffusion enables
topology-aware graph-level readout and node-level global reconstruction by allowing graph
embeddings and masked nodes to aggregate information from globally related regions. Extensive experiments across multiple neuroimaging
datasets with over 25,000 subjects and 60,000 scans involving various mental disorders and
brain atlases demonstrate consistent performance improvements.
Read the full abstract ▾
All authors Xinxu Wei, Rong Zhou, Lifang He, Yu Zhang
Machine Learning · Cross-listed from cs.CV
Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification
Yiqiao Li, Bo Shang and Jie Wei
Fine-grained truck classification is critical for intelligent transportation systems (ITS), yet current
LiDAR-based methods face scalability challenges due to their reliance on supervised deep learning and labor-intensive manual annotation.
Vision-
Language Models (VLMs) offer promising few-shot generalization, but their application to roadside
LiDAR is limited by a modality gap between sparse 3D point clouds and dense 2D imagery. We propose a framework that bridges this gap by adapting off-the-shelf VLMs for fine-grained truck classification without parameter fine-tuning. Our new depth-aware image generation pipeline applies noise removal, spatial and temporal registration, orientation rectification, morphological operations, and anisotropic smoothing to transform sparse, occluded
LiDAR scans into depth-encoded 2D visual proxies. Validated on a real-world
dataset of 20 vehicle classes, our approach achieves competitive classification accuracy with as few as 16-30 examples per class, offering a scalable alternative to data-intensive supervised baselines. We further observe a "Semantic Anchor" effect: text-based guidance regularizes performance in ultra-low-shot regimes $k < 4$, but degrades accuracy in more-shot settings due to semantic mismatch. Furthermore, we demonstrate the efficacy of this framework as a Cold Start strategy, using VLM-generated labels to bootstrap lightweight supervised models. Notably, the few-shot VLM-based model achieves over correct classification rate of 75 percent for specific drayage categories (20ft, 40ft, and 53ft containers) entirely without the costly training or fine-tuning, significantly reducing the intensive demands of initial manual labeling, thus achieving a method of practical use in ITS applications.
Read the full abstract ▾
Machine Learning
Reward-Guided Discrete Diffusion via Clean-Sample Markov Chain for Molecule and Biological Sequence Design
Prin Phunyaphibarn and Minhyuk Sung
Discrete
diffusion models have recently emerged as a powerful class of generative models for chemistry and biology data. In these fields, the goal is to generate various samples with high rewards (e.g., drug-likeness in molecules), making reward-based guidance crucial. Most existing methods are based on guiding the
diffusion model using intermediate rewards but tend to underperform since intermediate rewards are noisy due to the non-smooth nature of reward functions used in scientific domains. To address this, we propose Clean-Sample Markov Chain (CSMC) Sampler, a method that performs effective test-time reward-guided sampling for discrete
diffusion models, enabling local search without relying on intermediate rewards. CSMC constructs a Markov chain of clean samples using the Metropolis-Hastings
algorithm such that its stationary distribution is the target distribution. We design a proposal distribution by sequentially applying the forward and backward
diffusion processes, making the acceptance probability tractable. Experiments on molecule and biological sequence generation with various reward functions demonstrate that our method consistently outperforms prior approaches that rely on intermediate rewards.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
Xinyu Wang, Ke Deng, Fei Dou et al. (+2 more)
Model merging aims to combine multiple fine-tuned models into a single multi-task model without access to training data. Existing task-vector merging methods such as TIES, TSV-M, and Iso-C/CTS differ in their aggregation rules but treat all layers nearly uniformly. This assumption overlooks the strong layer-wise heterogeneity in large
vision transformers, where shallow layers are sensitive to interference while deeper layers encode stable task-specific features. We introduce LARV, a training-free, data-free, merger-agnostic Layer-wise Adaptive Rescaling Veneer that plugs into any task-vector merger and assigns a per-layer scale to each task vector before aggregation, and show it consistently boosts diverse merging rules. LARV adaptively suppresses shallow-layer interference and amplifies deeper-layer
alignment using a simple deterministic schedule, requiring no retraining or modification to existing mergers. To our knowledge, this is the first work to perform layer-aware scaling for task-vector merging. LARV computes simple data-free layer proxies and turns them into scales through a lightweight rule; we study several instantiations within one framework (e.g., tiered two/three-level scaling with fixed values, or continuous mappings) and show that tiered choices offer the best robustness, while continuous mappings remain an ablation. LARV is orthogonal to the base merger and adds negligible cost. On FusionBench with
Vision Transformers, LARV consistently improves all task-vector baselines across 8/14/20-task settings; for example, Iso-C + LARV reaches 85.9% on ViT-B/32, 89.2% on ViT-B/16, and 92.6% on ViT-L/14. Layerwise analysis and corruption tests further indicate that LARV suppresses shallow-layer interference while modestly amplifying deeper, task-stable features, turning model merging into a robust, layer-aware procedure rather than a uniform one.
Read the full abstract ▾
All authors Xinyu Wang, Ke Deng, Fei Dou, Jinbo Bi, Jin Lu
Machine Learning · Cross-listed from stat.ML
Is Memorization Helpful or Harmful? Prior Information Sets the Threshold
Chen Cheng and Rina Foygel Barber
We examine the connection between training error and generalization error for arbitrary estimating procedures, working in an overparameterized linear model under general priors in a
Bayesian setup. We find determining factors inherent to the prior distribution $\pi$, giving explicit conditions under which optimal generalization necessitates that the training error be (i) near interpolating relative to the noise size (i.e., memorization is necessary), or (ii) close to the noise level (i.e., overfitting is harmful). Remarkably, these phenomena occur when the noise reaches thresholds determined by the Fisher information and the variance parameters of the prior $\pi$.
Read the full abstract ▾
Machine Learning
Learning with Multiple Correct Answers – Regret Bounds under Different Feedback Models
Alireza F. Pour, Farnam Mansouri and Shai Ben-David
We study the problem of learning with multiple correct answers, where each instance admits a set of valid labels. We primarily focus on the online setup, where in each round the learner must output a valid label for the queried example. This setting is motivated by
language generation, in which a
prompt may admit many acceptable completions, but not every completion is acceptable. We study this problem under three feedback models. For each model, we characterize the optimal mistake bound in the realizable setting using an appropriate combinatorial dimension. We then show that the rate of regret can be constant, linear, or sublinear across the three models in the agnostic setting. Our results also imply sample complexity bounds for the batch setup that depend on the respective combinatorial dimensions.
Read the full abstract ▾
Machine Learning
Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
Nilaksh, Antoine Clavaud, Mathieu Reymond et al. (+2 more)
In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes
agents notoriously sample-inefficient, since value-based losses alone struggle to extract meaningful representations from transient data. We propose extending Self-Predictive Representations (SPR) to the streaming pipeline to maximize the utility of every observed frame. However, due to the highly correlated samples induced by the streaming regime, naively applying this auxiliary loss results in training instabilities. Thus, we introduce orthogonal gradient updates relative to the momentum target and resolve gradient conflicts arising from streaming-specific optimizers. Validated across the Atari, MinAtar, and Octax suites, our approach systematically outperforms existing streaming baselines. Latent-space analysis, including t-SNE visualizations and effective-rank measurements, confirms that our method learns significantly richer representations, bridging the performance gap caused by the absence of a replay buffer, while remaining efficient enough to train on just a few CPU cores.
Read the full abstract ▾
All authors Nilaksh, Antoine Clavaud, Mathieu Reymond, François Rivest, Sarath Chandar
Machine Learning
Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning
Yifei Cheng, Xianglin Yang, Guoxia Wang et al. (+5 more)
Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the computation cost, which becomes the bottleneck of SAM in the practical implementation. In this work, we propose an approach SL-SAM to break this bottleneck by introducing the sparse technique to layers. Our key innovation is to frame the dynamic selection of layers for both the gradient ascent (perturbation) and descent (update) steps as a multi-armed bandit problem. At the beginning of each iteration, SL-SAM samples a part of the layers of the model according to the gradient norm to participate in the backpropagation of the following parameter perturbation and update steps, thereby reducing the computation complexity. We then provide the analysis to guarantee the convergence of SL-SAM. In the experiments of fine-tuning models in several tasks, SL-SAM achieves the performances comparable to the state-of-the-art baselines, including a \#1 rank on LLM fine-tuning. Meanwhile, SL-SAM significantly reduces the ratio of active parameters in backpropagation compared to vanilla SAM (SL-SAM activates 47%, 22% and 21% parameters on the
vision, moderate and large
language model respectively while vanilla SAM always activates 100%), verifying the efficiency of our proposed
algorithm.
Read the full abstract ▾
All authors Yifei Cheng, Xianglin Yang, Guoxia Wang, Chao Huang, Fei Ma, Dianhai Yu, Xiaochun Cao, Li Shen
Machine Learning · Cross-listed from stat.ML
The Critical Horizon: Inspection Design Principles for Multi-Stage Operations and Deep Reasoning
Seyed Morteza Emadi
Manufacturing lines, service journeys, supply chains, and AI
reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We establish an information-theoretic barrier to this credit assignment problem: the signal connecting early steps to final outcomes decays exponentially with depth, creating a critical horizon beyond which reliable learning from endpoint data alone requires exponentially many samples. We prove four results. First, a Signal Decay Bound: sample complexity for attributing outcomes to early stages grows exponentially in the number of intervening steps. Second, Width Limits: parallel rollouts provide only logarithmic relief, with correlation capping the effective number of independent samples. Third, an Objective Mismatch: additive reward aggregation optimizes the wrong quantity when sequential validity requires all steps to be correct. Fourth, Optimal Inspection Design: uniform checkpoint spacing is minimax-optimal under homogeneous signal attenuation, while a greedy
algorithm yields optimal non-uniform schedules under heterogeneous attenuation. Together, these results provide a common analytical foundation for inspection design in operations and supervision design in AI.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.AS
TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymization
Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah et al. (+1 more)
Real-time voice conversion and speaker anonymization require causal, low-latency synthesis without sacrificing intelligibility or naturalness. Current systems have a core representational mismatch: content is time-varying, while speaker identity is injected as a static global
embedding. We introduce a streamable
speech synthesizer that aligns the temporal granularity of identity and content via a content-synchronous, time-varying timbre (TVT) representation. A Global Timbre
Memory expands a global timbre instance into multiple compact facets; frame-level content attends to this
memory, a gate regulates variation, and spherical interpolation preserves identity geometry while enabling smooth local changes. In addition, a factorized vector-quantized bottleneck regularizes content to reduce residual speaker leakage. The resulting system is streamable end-to-end, with <80 ms GPU latency. Experiments show improvements in naturalness, speaker transfer, and anonymization compared to SOTA streaming baselines, establishing TVT as a scalable approach for
privacy-preserving and expressive
speech synthesis under strict latency budgets.
Read the full abstract ▾
All authors Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna
Machine Learning
Latent Poincaré Shaping for Agentic Reinforcement Learning
Hanchen Xia, Baoyou Chen, Zelin Zang et al. (+3 more)
We propose LaPha, a method for training AlphaZero-like LLM
agents in a Poincaré latent space. Under LaPha, the search process can be visualized as a tree rooted at the
prompt and growing outward from the origin toward the boundary of the Poincaré ball, where negative
curvature provides exponentially increasing capacity with radius. Using
hyperbolic geodesic distance to rule-verified correctness, we define a node potential and assign dense process rewards by potential differences. We further attach a lightweight value head on the same shared latent space, enabling self-guided test-time scaling with almost no additional overhead. On MATH-500, LaPha improves Qwen2.5-Math-1.5B from 66.0% to 88.2%. With value-head-guided search, LaPha-1.5B reaches 56.7% accuracy on AIME'24, and LaPha-7B further achieves 60.0% on AIME'24 and 53.3% on AIME'25.
Read the full abstract ▾
All authors Hanchen Xia, Baoyou Chen, Zelin Zang, Yutang Ge, Guojiang Zhao, Siyu Zhu
Machine Learning
Large Language Models for Designing Participatory Budgeting Rules
Nguyen Thach, Xingchen Sha and Hau Chan
Participatory budgeting (PB) is a democratic paradigm for deciding the funding of public projects given the residents' preferences, which has been adopted in numerous cities across the world. The main focus of PB is designing rules, functions that return feasible budget allocations for a set of projects subject to some budget constraint. Designing PB rules that optimize both utility and
fairness objectives based on
agent preferences had been challenging due to the extensive domain knowledge required and the proven trade-off between the two notions. Recently, large
language models (LLMs) have been increasingly employed for automated algorithmic design. Given the resemblance of PB rules to
algorithms for classical knapsack problems, in this paper, we introduce a novel framework, named LLMRule, that addresses the limitations of existing works by incorporating LLMs into an evolutionary search procedure for automating the design of PB rules. Our experimental results, evaluated on more than 600 real-world PB instances obtained from the U.S., Canada, Poland, and the Netherlands with different representations of
agent preferences, demonstrate that the LLM-generated rules generally outperform existing handcrafted rules in terms of overall utility while still maintaining a similar degree of
fairness.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
Mykola Khandoga, Rui Yuan and Vinay Kumar Sankarapu
Policy gradient methods for
language model
reasoning, such as GRPO and DAPO, assign uniform credit to all generated
tokens - the filler phrase "Let me think" receives the same gradient update as the critical calculation "23 + 45 = 68." We propose counterfactual importance weighting: mask
reasoning spans, measure the drop in answer probability, and upweight
tokens accordingly during policy gradient updates. Our method requires no auxiliary models or external annotation, instead importance is estimated directly from the policy model's own probability shifts. Experiments on GSM8K across three models spanning the Qwen and Llama families demonstrate consistent improvements over uniform baselines and faster convergence to equivalent accuracy. Inverting the importance signal hurts performance, confirming we capture genuine causal structure rather than noise. Analysis shows the method correctly prioritizes calculation steps over scaffolding text. We view these findings as establishing counterfactual importance weighting as a foundation for further research rather than a complete solution.
Read the full abstract ▾
Machine Learning
MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection
Xueying Ding, Simon Klüttermann, Haomin Wen et al. (+2 more)
Quality
benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological choices. Outlier detection (OD) on tabular data underpins numerous real-world applications, yet existing OD
benchmarks remain limited. The prominent OD
benchmark AdBench is the de facto standard in the literature, yet comprises only 57
datasets. In addition to other shortcomings discussed in this work, its small scale severely restricts diversity and statistical power. We introduce MacrOData, a large-scale
benchmark suite for tabular OD comprising three carefully curated components: OddBench, with 790
datasets containing real-world semantic anomalies; OvrBench, with 856
datasets featuring real-world statistical outliers; and SynBench, with 800 synthetically generated
datasets spanning diverse data priors and outlier archetypes. Owing to its scale and diversity, MacrOData enables comprehensive and statistically robust evaluation of tabular OD methods. Our
benchmarks further satisfy several key desiderata: We provide standardized train/test splits for all
datasets, public/private
benchmark partitions with held-out test labels for the latter reserved toward an online leaderboard, and annotate our
datasets with semantic metadata. We conduct extensive experiments across all
benchmarks, evaluating a broad range of OD methods comprising classical, deep, and foundation models, over diverse hyperparameter configurations. We report detailed empirical findings, practical guidelines, as well as individual performances as references for future research. All
benchmarks containing 2,446
datasets combined are open-sourced, along with a publicly accessible leaderboard hosted at https://huggingface.co/MacrOData-CMU.
Read the full abstract ▾
All authors Xueying Ding, Simon Klüttermann, Haomin Wen, Yilong Chen, Leman Akoglu
Machine Learning
In-Hospital Stroke Risk-State Classification from PPG-Derived Hemodynamic Features
Jiaming Liu, Cheng Ding, Jian Wu et al. (+2 more)
The scarcity of temporally aligned pre-event physiological data limits the study of stroke risk states before documented clinical recognition. We focus on patients who experienced stroke during hospitalization while undergoing continuous monitoring, enabling retrospective analysis of pre-anchor photoplethysmography (PPG). Using MIMIC-III and MC-MED, an LLM-assisted pipeline generated candidate stroke anchors from unstructured notes. All retained anchors underwent physician adjudication, and a stratified 100-case double-review audit showed 95.0% candidate-to-adjudicated agreement within +/-15 min. We identified 176 MIMIC-III patients and 154 MC-MED patients with eligible synchronized pre-anchor PPG. A fixed 17-channel hemodynamic representation and ResNet-1D classifier were evaluated using patient-level five-fold internal validation and frozen external testing. At validation-selected operating points, F1-scores were 0.7956, 0.8759, and 0.9406 for 4-, 5-, and 6-hour horizons in MIMIC-III and 0.9256, 0.9595, and 0.9888 in MC-MED; the corresponding threshold-free AUCs ranged from 0.6124 to 0.7079. The PPG model achieved higher F1 than four non-waveform clinical and structured-EHR comparators in all six cohort-horizon settings. On high-risk non-stroke controls, window-level false-positive rates ranged from 0.1371 to 0.2938 and decreased to 0.0183-0.1739 after persistence aggregation. These retrospective findings support measurable pre-anchor PPG structure, but do not establish biological stroke onset, a calibrated bedside alarm, or a clinically validated prediction lead time.
Read the full abstract ▾
All authors Jiaming Liu, Cheng Ding, Jian Wu, Hongxia Xu, Daoqiang Zhang
Machine Learning
Priority-Aware Shapley Value
Kiljae Lee, Ziqi Liu, Weijing Tang et al. (+1 more)
Shapley values are widely used for model-agnostic data valuation and feature attribution, yet they implicitly assume contributors are interchangeable. This can be problematic when contributors are dependent (e.g., reused/augmented data or causal feature orderings) or when contributions should be adjusted by factors such as trust or risk. We propose Priority-Aware Shapley Value (PASV), which incorporates both hard precedence constraints and soft, contributor-specific priority weights. PASV is applicable to general precedence structures, recovers precedence-only and weight-only Shapley variants as special cases, and is uniquely characterized by natural axioms. We develop an efficient adjacent-swap Metropolis-Hastings sampler for scalable Monte Carlo estimation and analyze limiting regimes induced by extreme priority weights. Experiments on data valuation (MNIST/CIFAR10) and feature attribution (Census Income) demonstrate more structure-faithful allocations and a practical sensitivity analysis via our proposed "priority sweeping".
Read the full abstract ▾
All authors Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang
Machine Learning
SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
Ya-Chi Chu, Alkiviades Boukas and Madeleine Udell
Neural networks are increasingly used as fast surrogate models across various domains, but unconstrained predictions can violate physical, operational, or safety requirements. We propose SnareNet, a feasibility-controlled architecture to learn mappings whose outputs must satisfy input-dependent constraints. SnareNet appends a differentiable repair layer that navigates in the constraint map's range space, steering iterates toward feasibility and producing a repaired output that satisfies constraints to a user-specified tolerance. We stabilize end-to-end training by adaptive relaxation, a new training paradigm that snares the neural network at initialization and shrinks it into the feasible set, enabling early exploration and strict feasibility later in training. On optimization learning and trajectory planning
benchmarks, SnareNet consistently attains improved objective quality while satisfying constraints more reliably than prior work, and it is the first to enforce non-convex constraints at medium-to-high precision robustly across instances.
Read the full abstract ▾
Machine Learning
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Zhendong Mi, Yixiao Chen, Pu Zhao et al. (+4 more)
Mixture-of-Experts (MoE) based Large
Language Models (LLMs) have achieved superior performance, yet the massive
memory overhead caused by storing multiple expert networks severely hinders their practical deployment. Singular Value Decomposition (SVD)-based compression has emerged as a promising post-training technique; however, most existing methods apply uniform rank allocation or rely solely on static weight properties. This overlooks the substantial heterogeneity in expert utilization observed in MoE models, where frequent routing patterns and intrinsic information density vary significantly across experts. In this work, we propose RFID-MoE, an effective framework for MoE compression by exploiting heterogeneous Routing Frequency and Information Density. We first introduce a fused metric that combines expert activation frequency with effective rank to measure expert importance, adaptively allocating higher ranks to critical expert groups under a fixed budget. Moreover, instead of discarding compression residuals, we reconstruct them via a parameter-efficient sparse projection mechanism to recover lost information with minimal parameter overhead. Extensive experiments on representative MoE LLMs (e.g., Qwen3, DeepSeekMoE) across multiple compression ratios demonstrate that RFID-MoE consistently outperforms state-of-the-art methods like MoBE and D2-MoE. Notably, RFID-MoE achieves a perplexity of 16.92 on PTB with the Qwen3-30B model at a 60% compression ratio, reducing perplexity by over 8.0 compared to baselines, and improves zero-shot accuracy on HellaSwag by approximately 8%.
Read the full abstract ▾
All authors Zhendong Mi, Yixiao Chen, Pu Zhao, Xiaodong Yu, Hao Wang, Yanzhi Wang, Shaoyi Huang
Machine Learning
Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory
Runa Eschenhagen, Anna Cai, Tsung-Hsien Lee et al. (+1 more)
Optimizers leveraging the
matrix structure in neural networks, such as Shampoo and
Muon, are more data-efficient than element-wise
algorithms like Adam and Signum. While in specific settings, Shampoo and
Muon reduce to spectral descent analogous to how Adam and Signum reduce to sign descent, their general relationship and relative data efficiency under controlled settings remain unclear. Through extensive experiments on
language models, we demonstrate that Shampoo achieves higher
token efficiency than
Muon, mirroring Adam's advantage over Signum. We show that Shampoo's update applied to weight
matrices can be decomposed into an adapted
Muon update. Consistent with this, Shampoo's benefits can be exclusively attributed to its application to weight
matrices, challenging interpretations agnostic to parameter shapes. This admits a new perspective that also avoids shortcomings of related interpretations based on variance adaptation and whitening: rather than enforcing semi-orthogonality as in spectral descent, Shampoo's updates are time-averaged semi-orthogonal in expectation.
Read the full abstract ▾
All authors Runa Eschenhagen, Anna Cai, Tsung-Hsien Lee, Hao-Jun Michael Shi
Machine Learning · Cross-listed from cs.CL
Don't Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention
Shu-Ting Pi, Pradeep Bagavan, Yejia Li et al. (+2 more)
Utilizing Large
Language Models (LLM) as chatbots in diverse business scenarios often presents the challenge of maintaining topic continuity. Abrupt shifts in topics can lead to poor user experiences and inefficient utilization of computational resources. In this paper, we present a topic continuity model aimed at assessing whether a response aligns with the initial conversation topic. Our model is built upon the expansion of the corresponding natural
language understanding (NLU) model into quantifiable terms using a Naive Bayes approach. Subsequently, we have introduced an
attention mechanism and logarithmic nonlinearity to enhance its capability to capture topic continuity. This approach allows us to convert the NLU model into an interpretable analytical formula. In contrast to many NLU models constrained by
token limits, our proposed model can seamlessly handle conversations of any length with linear time complexity. Furthermore, the
attention mechanism significantly improves the model's ability to identify topic continuity in complex conversations. According to our experiments, our model consistently outperforms traditional methods, particularly in handling lengthy and intricate conversations. This unique capability offers us an opportunity to ensure the responsible and interpretable use of LLMs.
Read the full abstract ▾
All authors Shu-Ting Pi, Pradeep Bagavan, Yejia Li, Disha, Qun Liu
Machine Learning · Cross-listed from cond-mat.mtrl-sci
How Far Can You Grow? Characterizing the Extrapolation Frontier of Graph Generative Models for Materials Science
Can Polat, Erchin Serpedin, Mustafa Kurban et al. (+1 more)
Every generative model for crystalline materials harbors a critical structure size beyond which its outputs become unreliable; we call this the extrapolation frontier. Despite its consequences for nanomaterial design, this frontier has never been systematically measured. We introduce RADII, a radius-resolved
benchmark of ~75,000
crystal-derived nanoparticle structures (33-11,298 atoms) that treats radius as a continuous scaling knob, tracing generation quality from in- to out-of-distribution under leakage-free splits. Each model is conditioned on target composition and atom count, isolating
geometric extrapolation as the evaluation variable. RADII provides frontier-specific diagnostics: per-radius error profiles pinpoint each architecture's scaling ceiling, surface-interior decomposition separates boundary from bulk failures, and cross-metric sequencing reveals which aspect of structural fidelity breaks first. Benchmarking five state-of-the-art architectures, we find that: (i) well-behaved models degrade by ~13% in global positional error beyond training radii, while divergent models show poor fidelity across scales, with local bond fidelity ranging from negligible degradation to over 2x error growth; (ii) no two architectures share a failure sequence, revealing the frontier as a multi-dimensional surface shaped by model family; and (iii) well-behaved models follow the expected
geometric scaling exponent alpha ~ 1/3, whose in-distribution fit predicts out-of-distribution error, making frontiers forecastable. Scaling MatterGen to its published parameter count stabilizes sampling but does not close the frontier, while DiffCSP remains unstable at published scale. These findings establish output scale as a first-class evaluation axis for
geometric generative models. Code and data: https://github.com/KurbanIntelligenceLab/RADII.
Read the full abstract ▾
All authors Can Polat, Erchin Serpedin, Mustafa Kurban, Hasan Kurban
Machine Learning
Empowering Contrastive Federated Sequential Recommendation with LLMs
Thi Minh Chau Nguyen, Minh Hieu Nguyen, Duc Anh Nguyen et al. (+3 more)
Federated sequential recommendation (FedSeqRec) aims to perform next-item prediction while keeping user data decentralised, yet model quality is frequently constrained by fragmented, noisy, and homogeneous interaction logs stored on individual devices. Many existing approaches attempt to compensate through manual data augmentation or additional server-side constraints, but these strategies either introduce limited semantic diversity or increase system overhead. To overcome these challenges, we propose LUMOS, a parameter-isolated FedSeqRec architecture that integrates large
language models (LLMs) as local semantic generators. Instead of sharing gradients or auxiliary parameters, LUMOS privately invokes an on-device LLM to construct three complementary sequence variants from each user history: (i) future-oriented trajectories that infer plausible behavioural continuations, (ii) semantically equivalent rephrasings that retain user intent while diversifying interaction patterns, and (iii) preference-inconsistent counterfactuals that serve as informative negatives. These synthesized sequences are jointly encoded within the
federated backbone through a tri-view contrastive optimisation scheme, enabling richer representation learning without exposing sensitive information. Experimental results across three public
benchmarks show that LUMOS achieves consistent gains over competitive centralised and
federated baselines on HR@20 and NDCG@20. In addition, the use of semantically grounded positive signals and counterfactual negatives improves robustness under noisy and
adversarial environments, even without dedicated server-side protection modules. Overall, this work demonstrates the potential of LLM-driven semantic generation as a new paradigm for advancing
privacy-preserving
federated recommendation.
Read the full abstract ▾
All authors Thi Minh Chau Nguyen, Minh Hieu Nguyen, Duc Anh Nguyen, Xuan Huong Tran, Thanh Trung Huynh, Quoc Viet Hung Nguyen
Machine Learning
Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
Pei-Chi Pan, Yingbin Liang and Sen Lin
Large
Language Models (LLMs) demonstrate transformative potential, yet their
reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is fundamentally governed by reward design. Despite its importance, the relationship between reward modeling and core LLM challenges–such as evaluation bias,
hallucination, distribution shift, and efficient learning–remains poorly understood. This work argues that reward modeling is not merely an implementation detail but a central architect of
reasoning alignment, shaping what models learn, how they generalize, and whether their outputs can be trusted. We introduce
Reasoning-Aligned Reinforcement Learning (RARL), a
reasoning-centric taxonomic perspective that organizes diverse reward paradigms for multi-step
reasoning. Within this perspective, we present a taxonomy of reward mechanisms, analyze reward hacking as a pervasive failure mode, and examine how reward signals unify challenges ranging from inference-time scaling to
hallucination mitigation. We further critically evaluate existing
benchmarks, highlighting vulnerabilities such as data contamination and reward misalignment, and outline directions for more robust evaluation. By integrating fragmented research threads and clarifying the interplay between reward design and fundamental
reasoning capabilities, this work provides a foundational roadmap for building
reasoning models that are robust, verifiable, and trustworthy.
Read the full abstract ▾