Machine Learning
Disentangled Representation Learning through Unsupervised Symmetry Group Discovery
Barthélémy Dang-Nhu, Louis Annabi and Sylvain Argentieri
Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to
symmetry-based disentanglement have required strong prior knowledge of the
symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an
embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true
symmetry group decomposition under minimal assumptions, and derive two
algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear
Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches.
Read the full abstract ▾
Machine Learning
Language Generation with Replay: A Learning-Theoretic View of Model Collapse
Giorgio Racca, Michal Valko and Amartya Sanyal
As scaling laws push the training of frontier large
language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. In practice, model developers address this concern through data cleaning, watermarking, synthetic-data policies, or, in some cases, blissful ignorance. However, the problem of model collapse in generative models has not been examined from a learning-theoretic perspective: we study it through the theoretical lens of the
language generation in the limit framework, introducing a replay adversary that augments the example stream with the generator's own past outputs. Our main contribution is a fine-grained learning-theoretic characterization of when replay fundamentally limits generation: while replay is benign for the strongest notion of uniform generation, it provably creates separations for the weaker notions of non-uniform generation and generation in the limit. Interestingly, our positive results mirror heuristics widely used in practice, such as data cleaning, watermarking, and output filtering, while our separations show when these ideas can fail.
Read the full abstract ▾
Machine Learning
A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for $m$-Set Semi-Bandit Problem
Botao Chen, Jongyeong Lee, Chansoo Kim et al. (+1 more)
This paper studies the optimality and complexity of Follow-the-Perturbed-Leader (FTPL) policy in $m$-set semi-bandit problems. FTPL has been studied extensively as a promising candidate of an efficient
algorithm with favorable regret for
adversarial combinatorial semi-bandits. Nevertheless, the optimality of FTPL has still been unknown unlike Follow-the-Regularized-Leader (FTRL) whose optimality has been proved for various tasks of online learning. In this paper, we extend the analysis of FTPL with
geometric resampling (GR) to $m$-set semi-bandits, which is a special case of combinatorial semi-bandits, showing that FTPL with Fréchet and Pareto distributions with certain parameters achieves the best possible regret of $O(\sqrt{mdT})$ in
adversarial setting. We also show that FTPL with Fréchet and Pareto distributions with a certain parameter achieves a logarithmic regret for
stochastic setting, meaning the Best-of-Both-Worlds optimality of FTPL for $m$-set semi-bandit problems. Furthermore, we extend the conditional
geometric resampling to $m$-set semi-bandits for efficient loss estimation in FTPL, reducing the computational complexity from $O(d^2)$ of the original
geometric resampling to $O(md(\log(d/m)+1))$ without sacrificing the regret performance.
Read the full abstract ▾
All authors Botao Chen, Jongyeong Lee, Chansoo Kim, Junya Honda
Machine Learning · Cross-listed from cs.HC
Modeling Trial-and-Error Navigation With a Sequential Decision Model of Information Scent
Xiaofu Jin, Yunpeng Bai and Antti Oulasvirta
Users often struggle to locate an item within an information architecture, particularly when links are ambiguous or deeply nested in hierarchies. Information scent has been used to explain why users select incorrect links, but this concept assumes that users see all available links before deciding. In practice, users frequently select a link too quickly, overlook relevant cues, and then rely on backtracking when errors occur. We extend the concept of information scent by framing
navigation as a sequential decision-making problem under
memory constraints. Specifically, we assume that users do not scan entire pages but instead inspect strategically, looking "just enough" to find the target given their time budget. To choose which item to inspect next, they consider both local (this page) and global (site) scent; however, both are constrained by
memory. Trying to avoid wasting time, they occasionally choose the wrong links without inspecting everything on a page. Comparisons with empirical data show that our model replicates key
navigation behaviors: premature selections, wrong turns, and recovery from backtracking. We conclude that trial-and-error behavior is well explained by information scent when accounting for the sequential and bounded characteristics of the
navigation problem.
Read the full abstract ▾
Machine Learning
Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach
Erfan Mirzaei, Seyed Pooya Shariatpanahi, Alireza Tavakoli et al. (+2 more)
Personalized AI-based services involve a population of individual reinforcement learning
agents. However, most reinforcement learning
algorithms focus on harnessing individual learning and fail to leverage the social learning capabilities commonly exhibited by humans and animals. Social learning integrates individual experience with observing others' behavior, presenting opportunities for improved learning outcomes. In this study, we focus on a social bandit learning scenario where a social
agent observes other
agents' actions without knowledge of their rewards. The
agents independently pursue their own policy without explicit motivation to teach each other. We propose a free energy-based social bandit learning
algorithm over the policy space, where the social
agent evaluates others' expertise levels without resorting to any oracle or social norms. Accordingly, the social
agent integrates its direct experiences in the environment and others' estimated policies. The theoretical convergence of our
algorithm to the optimal policy is proven. Empirical evaluations validate the superiority of our social learning method over alternative approaches in various scenarios. Our
algorithm strategically identifies the relevant
agents, even in the presence of random or suboptimal
agents, and skillfully exploits their behavioral information. In addition to societies including expert
agents, in the presence of relevant but non-expert
agents, our
algorithm significantly enhances individual learning performance, where most related methods fail. Importantly, it also maintains logarithmic regret.
Read the full abstract ▾
All authors Erfan Mirzaei, Seyed Pooya Shariatpanahi, Alireza Tavakoli, Reshad Hosseini, Majid Nili Ahmadabadi
Machine Learning · Cross-listed from cs.AI
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
David Baumgartner, Eliezer de Souza da Silva and Iñigo Urteaga
Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing observed data likelihood. However, likelihood in observation space measures marginal density rather than conformity to structured temporal dynamics, and therefore can assign high probability to anomalous or out-of-distribution samples. We address this structural limitation by relocating the notion of anomaly to a prescribed latent space. We introduce explicit inductive biases in conditional normalizing flows, modeling time-series observations within a discrete-time state-space framework that constrains latent representations to evolve according to prescribed temporal dynamics. Under this formulation, expected behavior corresponds to compliance with a specified distribution over latent trajectories, while anomalies are defined as violations of these dynamics. Anomaly detection is consequently reformulated as a statistically grounded compliance test, such that observations are mapped to latent space and evaluated via goodness-of-fit tests against the prescribed latent
evolution. This yields a principled decision rule that remains effective even in regions of high observation likelihood. Experiments on synthetic and real-world time-series demonstrate reliable detection of anomalies in frequency, amplitude, and observation noise, while providing interpretable diagnostics of model compliance.
Read the full abstract ▾
Machine Learning
Mitigating the Multiplicity Burden: The Role of Calibration in Reducing Predictive Multiplicity of Classifiers
Mustafa Cavus
As machine learning models are increasingly deployed in high-stakes environments, ensuring both probabilistic reliability and prediction stability has become critical. This paper examines the interplay between classification calibration and predictive multiplicity - the phenomenon in which multiple near-optimal models within the Rashomon set yield conflicting credit outcomes for the same applicant. Using nine diverse credit risk
benchmark datasets, we investigate whether predictive multiplicity concentrates in regions of low predictive confidence and how post-hoc calibration can mitigate algorithmic arbitrariness. Our empirical analysis reveals that minority class observations bear a disproportionate multiplicity burden, as confirmed by significant disparities in predictive multiplicity and prediction confidence. Furthermore, our empirical comparisons indicate that applying post-hoc calibration methods - specifically Platt Scaling, Isotonic Regression, and Temperature Scaling - is associated with lower obscurity across the Rashomon set. Among the tested techniques, Platt Scaling and Isotonic Regression provide the most robust reduction in predictive multiplicity. These findings suggest that calibration can function as a consensus-enforcing layer and may support procedural
fairness by mitigating predictive multiplicity.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
CINDI: Conditional Imputation and Noisy Data Integrity with Flows in Power Grid Data
David Baumgartner, Helge Langseth and Heri Ramampiaro
Real-world multivariate time series, particularly in critical infrastructure such as electrical power grids, are often corrupted by noise and anomalies that degrade the performance of downstream tasks. Standard data cleaning approaches often rely on disjoint strategies, which involve detecting errors with one model and imputing them with another. Such approaches can fail to capture the full joint distribution of the data and ignore prediction uncertainty. This work introduces Conditional Imputation and Noisy Data Integrity (CINDI), an unsupervised probabilistic framework designed to restore data integrity in complex time series. Unlike fragmented approaches, CINDI unifies anomaly detection and imputation into a single end-to-end system built on conditional normalizing flows. By modeling the exact conditional likelihood of the data, the framework identifies low-probability segments and iteratively samples statistically consistent replacements. This allows CINDI to efficiently reuse learned information while preserving the underlying physical and statistical properties of the system. We evaluate the framework using real-world grid loss data from a Norwegian power distribution operator, though the methodology is designed to generalize to any multivariate time series domain. The results demonstrate that CINDI yields robust performance compared to competitive baselines, offering a scalable solution for maintaining reliability in noisy environments.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction
Ammar Kheder, Helmi Toropainen, Wenqing Peng et al. (+3 more)
Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains required in real-world environmental monitoring. A single European air-quality map at 1 km resolution comprises 29 million pixels, far beyond the limits of naive self-
attention. We introduce CRAN-PM, a dual-branch
Vision Transformer that leverages cross-resolution
attention to efficiently fuse global meteorological data (25 km) with local high-resolution PM2.5 at the current time (1 km). Instead of including physically driven factors like temperature and topography as input, we further introduce elevation-aware self-
attention and wind-guided cross-
attention to force the network to learn physically consistent feature representations for PM2.5
forecasting. CRAN-PM is fully trainable and
memory-efficient, generating the complete 29-million-pixel European map in 1.8 seconds on a single GPU. Evaluated on daily PM2.5
forecasting throughout Europe in 2022 (362 days, 2,971 European Environment Agency (EEA) stations), it reduces RMSE by 4.7% at T+1 and 10.7% at T+3 compared to the best single-scale baseline, while reducing bias in complex terrain by 36%.
Read the full abstract ▾
All authors Ammar Kheder, Helmi Toropainen, Wenqing Peng, Samuel Antão, Zhi-Song Liu, Michael Boy
Machine Learning
EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering
Nicolas Deutschmann, Constance Ferragu, Jonathan D. Ziegler et al. (+2 more)
Protein optimization improves an existing
protein through targeted mutations, but existing
protein language models are poorly suited to it: autoregressive models require full sequence generation, masked
language and discrete
diffusion models rely on pre-specified mutation locations, and none naturally support insertions and deletions relative to a template. We introduce EvoFlows, a variable-length sequence-to-sequence approach that learns mutational trajectories between evolutionarily related
proteins via edit flows, predicting not only _which_ mutation to perform, but also _where_ and _how many_ should occur. Across diverse
protein families from UniRef and OAS, EvoFlows generates variants that remain consistent with natural families while exploring farther from the template than leading baselines. _In vitro_ validation of a VHH binder and an enzyme confirms that the large majority of generated variants remain functional and stable without computational downselection.
Read the full abstract ▾
All authors Nicolas Deutschmann, Constance Ferragu, Jonathan D. Ziegler, Shayan Aziznejad, Eli Bixby
Machine Learning · Cross-listed from stat.ML
Decomposing Observational Multiplicity in Decision Trees: Leaf and Structural Regret
Mustafa Cavus
Many machine learning tasks admit multiple models that perform almost equally well, a phenomenon known as predictive multiplicity. A fundamental source of this multiplicity is observational multiplicity, which arises from the
stochastic nature of label collection: observed training labels represent only a single realization of the underlying ground-truth probabilities. While theoretical frameworks for observational multiplicity have been established for logistic regression, their implications for non-smooth, partition-based models like decision trees remain underexplored. In this paper, we introduce two complementary notions of observational multiplicity for decision tree classifiers: leaf regret and structural regret. Leaf regret quantifies the intrinsic variability of predictions within a fixed leaf due to finite-sample noise, while structural regret captures variability induced by the instability of the learned tree structure itself. We provide a formal decomposition of observational multiplicity into these two components and establish statistical guarantees. Our experimental evaluation across diverse credit risk scoring
datasets confirms the near-perfect
alignment between our theoretical decomposition and the empirically observed variance. Notably, we find that structural regret is the primary driver of observational multiplicity, accounting for over 15 times the variability of leaf regret in some
datasets. Furthermore, we demonstrate that utilizing these regret measures as an abstention mechanism in selective prediction can effectively identify arbitrary regions and improve model safety, elevating recall from 92% to 100% on the most stable sub-populations. These results establish a rigorous framework for quantifying observational multiplicity, aligning with recent advances in algorithmic safety and interpretability.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Causal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2
Suvendu Sekhar Mohanty
We propose a novel causal prosody mediation framework for expressive text-to-
speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit
emotion conditioning and introduces counterfactual training objectives to disentangle emotional prosody from linguistic content. By formulating a structural causal model of how text (content),
emotion, and speaker jointly influence prosody (duration, pitch, energy) and ultimately the
speech waveform, we derive two complementary loss terms: an Indirect Path Constraint (IPC) to enforce that
emotion affects
speech only through prosody, and a Counterfactual Prosody Constraint (CPC) to encourage distinct prosody patterns for different
emotions. The resulting model is trained on multi-speaker emotional corpora (LibriTTS, EmoV-DB, VCTK) with a combined objective that includes standard spectrogram reconstruction and variance prediction losses alongside our causal losses. In evaluations on expressive
speech synthesis, our method achieves significantly improved prosody manipulation and
emotion rendering, with higher mean opinion scores (MOS) and
emotion accuracy than baseline FastSpeech2 variants. We also observe better intelligibility (low WER) and speaker consistency when transferring
emotions across speakers. Extensive ablations confirm that the causal objectives successfully separate prosody attribution, yielding an interpretable model that allows controlled counterfactual prosody editing (e.g. "same utterance, different
emotion") without compromising naturalness. We discuss the implications for identifiability in prosody modeling and outline limitations such as the assumption that
emotion effects are fully captured by pitch, duration, and energy. Our work demonstrates how integrating causal learning principles into TTS can improve controllability and expressiveness in generated
speech.
Read the full abstract ▾
Machine Learning
Entropy-Preserving Reinforcement Learning
Aleksei Petrenko, Ben Lipkin, Kevin Chen et al. (+4 more)
Policy gradient
algorithms have driven many recent advancements in
language model
reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative solutions. As we show in this paper, many policy gradient
algorithms naturally reduce the
entropy – and thus the diversity of explored trajectories – as part of training, yielding a policy increasingly limited in its ability to explore. In this paper, we argue that
entropy should be actively monitored and controlled throughout training. We formally analyze the contributions of leading policy gradient objectives on
entropy dynamics, identify empirical factors (such as numerical precision) that significantly impact
entropy behavior, and propose explicit mechanisms for
entropy control. These include REPO, a family of
algorithms that modify the advantage function to regulate
entropy, and ADAPO, an adaptive asymmetric clipping approach. Models trained with our
entropy-preserving methods maintain diversity throughout training, yielding final policies that are more performant and retain their trainability for sequential learning in new environments.
Read the full abstract ▾
All authors Aleksei Petrenko, Ben Lipkin, Kevin Chen, Erik Wijmans, Marco Cusumano-Towner, Raja Giryes, Philipp Krähenbühl
Machine Learning
Context-dependent manifold learning: A neuromodulated constrained autoencoder approach
Jérôme Adriaens, Gustave Bainier, Guillaume Drion et al. (+1 more)
Many physical systems exhibit a low-dimensional structure that varies with external parameters: link lengths in a
robot, forcing constants in a fluid, or Reynolds numbers in a flow shift the underlying
manifold while preserving its intrinsic dimension. Constrained AutoEncoders (cAEs) learn such
manifolds through an idempotent encoder-decoder projection, a property that unconstrained autoencoders cannot match and that is essential whenever the model is applied iteratively. However, the standard strategies for making a cAE context-dependent, namely concatenating the context to the input or affinely modulating hidden activations, break the encoder-decoder idempotency, sacrificing the projection guarantee precisely in the setting where it would be most valuable. To restore this guarantee under context variation, we developed the Neuromodulated Constrained Autoencoder (NcAE), which modulates the activation slope and bias of a cAE through a context-driven hyper-network. This paper presents the NcAE, its theoretical foundation, and its empirical validation. We prove that for every context, including contexts unseen at training time, the reconstruction map remains an idempotent projection, the
topology of the learned
manifold is invariant, and context perturbations induce smooth changes in the
manifold. We evaluated our approach on a 16-DoF pendulum with context-dependent coupling and the Lorenz96 system across a bifurcation. The NcAE matched or exceeded the best of six baselines on reconstruction, idempotency, and latent-geometry metrics, while being the only architecture that preserves
geometric consistency by construction. The NcAE thereby provides a stable, geometry-preserving coordinate system across families of physical regimes.
Read the full abstract ▾
All authors Jérôme Adriaens, Gustave Bainier, Guillaume Drion, Pierre Sacré
Machine Learning
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
Jiaheng Hu, Jay Shim, Chen Tang et al. (+4 more)
Continual Reinforcement Learning (CRL) for
Vision-
Language-Action (VLA) models is a promising direction toward self-improving
embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL for large pretrained VLAs across diverse lifelong RL
benchmarks. We find that, contrary to established belief, simple Seq. FT with low-rank adaptation (LoRA) is remarkably strong: it achieves high plasticity, exhibits little to no forgetting, and retains strong zero-shot generalization, frequently outperforming more sophisticated CRL methods. Through detailed analysis, we show that this robustness arises from a synergy between the large pretrained model, parameter-efficient adaptation, and on-policy RL. Together, these components reshape the stability-plasticity trade-off, making continual adaptation both stable and scalable. Our results position Sequential Fine-Tuning as a powerful method for continual RL with VLAs and provide new insights into lifelong learning in the large model era. Code is available at https://github.com/UT-Austin-RobIn/continual-vla-rl
Read the full abstract ▾
All authors Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martin-Martin
Machine Learning
Personalized Federated Learning via Gaussian Generative Modeling
Peng Hu and Jianwei Ma
Federated learning has emerged as a paradigm to train models collaboratively on inherently distributed client data while safeguarding
privacy. In this context, personalized
federated learning tackles the challenge of data heterogeneity by equipping each client with a dedicated model. A prevalent strategy decouples the model into a shared feature extractor and a personalized classifier head, where the latter actively guides the representation learning. However, previous works have focused on classifier head-guided personalization, neglecting the potential personalized characteristics in the representation distribution. Building on this insight, we propose pFedGM, a method based on Gaussian generative modeling. The approach begins by training a Gaussian generator that models client heterogeneity via weighted re-sampling. A balance between global collaboration and personalization is then struck by employing a dual objective: a shared objective that maximizes inter-class distance across clients, and a local objective that minimizes intra-class distance within them. To achieve this, we decouple the conventional Gaussian classifier into a navigator for global optimization, and a statistic extractor for capturing distributional statistics. Inspired by the Kalman gain, the
algorithm then employs a dual-scale fusion framework at global and local levels to equip each client with a personalized classifier head. In this framework, we model the global representation distribution as a prior and the client-specific data as the likelihood, enabling
Bayesian inference for class probability estimation. The evaluation covers a comprehensive range of scenarios: heterogeneity in class counts, environmental corruption, and multiple
benchmark datasets and configurations. pFedGM achieves superior or competitive performance compared to state-of-the-art methods.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild
Jiin Im, Sisung Liu and Je Hyeong Hong
Semantic correspondence is essential for handling diverse in-the-wild images lacking explicit correspondence annotations. While recent 2D foundation models offer powerful features, adapting them for unsupervised learning via nearest-neighbor pseudo-labels has key limitations: it operates locally, ignoring structural relationships, and consequently its reliance on 2D appearance fails to resolve
geometric ambiguities arising from
symmetries or repetitive features. In this work, we address this by reformulating pseudo-label generation as a Fused Gromov-Wasserstein (FGW) problem, which jointly optimizes inter-feature similarity and intra-structural consistency. Our framework, Shape-of-You (SoY), leverages a 3D foundation model to define this intra-structure in the
geometric space, resolving abovementioned ambiguity. However, since FGW is a computationally prohibitive quadratic problem, we approximate it through anchor-based linearization. The resulting probabilistic transport plan provides a structurally consistent but noisy supervisory signal. Thus, we introduce a soft-target loss dynamically blending guidance from this plan with network predictions to build a learning framework robust to this noise. SoY achieves state-of-the-art performance on SPair-71k and AP-10k
datasets, establishing a new
benchmark in semantic correspondence without explicit
geometric annotations. Code is available at Shape-of-You.
Read the full abstract ▾
Machine Learning
Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE
Mohammad Aflah Khan, Krishna P. Gummadi, Manish Gupta et al. (+1 more)
Rotary Positional
Embedding (RoPE) is widely used in
transformers to encode relative positional information, yet the effect of applying RoPE to only a subset of hidden dimensions remains underexplored. This design choice can substantially reduce
memory usage, especially at long context lengths. We show that partial RoPE achieves up to 10$\times$
memory savings over standard RoPE cache while maintaining comparable final loss. We systematically study its impact on training dynamics and convergence across architectures, model sizes, sequence lengths, and
datasets. Our results reveal that: (1) applying RoPE to only a small fraction of dimensions (around 10%) matches the convergence of full RoPE; (2) these trends remain consistent across settings; and (3) NoPE (No Positional Encoding) can produce loss spikes, which are mitigated by minimal RoPE usage or QK-Norm application. Overall, our findings highlight partial RoPE as an effective trade-off between efficiency and stability.
Read the full abstract ▾
All authors Mohammad Aflah Khan, Krishna P. Gummadi, Manish Gupta, Abhilasha Ravichander
Machine Learning
AutoScout: Structured Optimization for Automating ML System Configuration
Jimmy Shong, Yuhan Ding, Yihan Jiang et al. (+5 more)
Machine learning (ML) systems expose a rapidly expanding configuration space spanning model-parallelism strategies, communication optimizations, and low-level runtime parameters. End-to-end system efficiency is highly sensitive to these choices, yet identifying high-performance configurations is challenging due to heterogeneous feature types (e.g., sparse and dense parameters), conditional dependencies (e.g., valid execution parameters only under specific upstream decisions), and the high search (profiling) cost. Existing approaches either optimize a narrow subset of configuration dimensions or rely on ad-hoc heuristics that fail to generalize as configuration spaces continue to grow. We present AutoScout, a general-purpose systems configurator for ML training, fine-tuning, and inference. It formulates the system configuration as a mixed-discrete/continuous optimization problem with hierarchical dependencies and introduces a hybrid optimization framework that jointly refines sparse structural decisions and dense execution parameters. To reduce profiling cost, AutoScout adaptively prioritizes high-impact configuration features and ensembles simulators with varying fidelity. Across diverse models, hardware platforms, and deployment objectives, AutoScout consistently identifies high-performance configurations, achieving 2.7-3.0$\times$ training speedup over expert-tuned settings.
Read the full abstract ▾
All authors Jimmy Shong, Yuhan Ding, Yihan Jiang, Liheng Jing, Haonan Chen, Gaokai Zhang, Aditya Akella, Fan Lai
Machine Learning
Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization
Qijun Liao, Jue Yang, Yiting Kang et al. (+3 more)
Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms – assumed known a priori – directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization objective to enforce energy-efficient control. A complete theoretical foundation is established: functional independence of shaping and regularization, energy-based gradient enrichment under positive-definite Hessian conditions, convergence guarantees under function approximation, and approximate potential error bounds. Across four continuous control
benchmarks and four baseline
algorithms, H-EARS achieves consistent gains in convergence speed, policy stability, and final performance. High-fidelity vehicle simulations validate applicability in safety-critical settings under extreme road conditions.
Read the full abstract ▾
All authors Qijun Liao, Jue Yang, Yiting Kang, Xinxin Zhao, Yong Zhang, Mingan Zhao
Machine Learning
Survival Meets Classification: A Novel Framework for Early Risk Prediction Models of Chronic Diseases
Shaheer Ahmad Khan, Muhammad Usamah Shahid and Muddassar Farooq
Chronic diseases are long-lasting conditions that require lifelong medical
attention. Using big EMR data, we have developed early disease risk prediction models for five common chronic diseases: diabetes, hypertension, CKD, COPD, and chronic ischemic heart disease. In this study, we present a novel approach for disease risk models by integrating survival analysis with classification techniques. Traditional models for predicting the risk of chronic diseases predominantly focus on either survival analysis or classification independently. In this paper, we show survival analysis methods can be re-engineered to enable them to do classification efficiently and effectively, thereby making them a comprehensive tool for developing disease risk surveillance models. The results of our experiments on real-world big EMR data show that the performance of survival models in terms of accuracy, F1 score, and AUROC is comparable to or better than that of prior state-of-the-art models like LightGBM and XGBoost. Lastly, the proposed survival models use a novel methodology to generate explanations, which have been clinically validated by a panel of three expert physicians.
Read the full abstract ▾
Machine Learning
CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time
Nghia D. Nguyen, Pablo Robles-Granda and Lav R. Varshney
Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses a significant challenge in achieving accurate and efficient estimation. We introduce causal autoencoding and treatment conditioning (CAETC), a novel method for this problem. Built on
adversarial representation learning, our method leverages an autoencoding architecture to learn a partially invertible and treatment-invariant representation, where the outcome prediction task is cast as applying a treatment-specific conditioning on the representation. Our design is independent of the underlying sequence model and can be applied to existing architectures such as long short-term
memories (LSTMs) or temporal convolution networks (TCNs). We conduct extensive experiments on synthetic, semi-synthetic, and real-world data to demonstrate that CAETC yields significant improvement in counterfactual estimation over existing methods.
Read the full abstract ▾
Machine Learning
Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports
Liangkai Zhou, Susu Xu, Shuqi Zhong et al. (+1 more)
Many real-world machine learning tasks are anti-causal: they require inferring latent causes from observed effects. In practice, we often face multiple related tasks where the structural dependencies are a hybrid of task-invariant and task-specific mechanisms. We propose Multi-Task Anti-Causal learning (MTAC), a framework for estimating causes from outcomes and confounders by explicitly exploiting such cross-task invariances. MTAC learns a structural equation model (SEM) that factorizes the outcome-generation process into (i) a task-invariant mechanism and (ii) task-specific mechanisms via a shared backbone with task-specific deviations. Building on the learned forward model, MTAC performs maximum A posteriori (MAP) based inference to reconstruct causes by jointly optimizing latent mechanism variables and cause magnitudes under the learned structural model. We evaluate MTAC on the application of urban event reconstruction from resident reports, spanning three tasks: parking violations, abandoned properties, and unsanitary conditions. On real-world data collected from Manhattan and Newark, MTAC consistently improves reconstruction accuracy over strong baselines, achieving up to 33.04% MAE reduction and demonstrating the benefits of learning transferable mechanisms across tasks.
Read the full abstract ▾
All authors Liangkai Zhou, Susu Xu, Shuqi Zhong, Shan Lin
Machine Learning · Cross-listed from cs.CL
One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries
Mayank Saini and Arit Kumar Bishwas
We present an agentic AI framework for autonomous
multimodal query processing that coordinates specialized tools across text, image, audio,
video, and document modalities. A central Supervisor dynamically decomposes user queries, delegates subtasks to modality-appropriate tools (e.g., object detection, OCR,
speech transcription), and synthesizes results through adaptive routing strategies rather than predetermined decision trees. For text-only queries, the framework uses learned routing via RouteLLM, while non-text paths use SLM-assisted modality decomposition. Evaluated on 2,847 queries across 15 task categories, our framework achieves 72% reduction in time-to-accurate-answer, 85% reduction in conversational rework, and 67% cost reduction compared to the matched hierarchical baseline while maintaining accuracy parity. These results demonstrate that intelligent centralized orchestration fundamentally improves
multimodal AI deployment economics.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Simultaneous estimation of multiple discrete unimodal distributions under stochastic order constraints
Yasuhiro Yoshida, Noriyoshi Sukegawa and Jiro Iwanaga
We study the problem of estimating multiple discrete unimodal distributions, motivated by search behavior analysis on a real-world platform. To incorporate prior knowledge of precedence relations among distributions, we impose
stochastic order constraints and formulate the estimation task as a mixed-integer convex quadratic optimization problem. Experiments on both synthetic and real
datasets show that the proposed method reduces the Jensen-Shannon divergence by 2.2% on average (up to 6.3%) when the sample size is small, while performing comparably to existing methods when sufficient data are available.
Read the full abstract ▾
Machine Learning
CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement
Alex Gn, Fan Li, S Kuniyilh et al. (+1 more)
Modern wearable and mobile devices are equipped with inertial measurement units (IMUs). Human Activity Recognition (HAR) applications running on such devices use machine-learning-based, data-driven techniques that leverage such sensor data. However, sensor-data-driven HAR deployments face two critical challenges: protecting sensitive user information embedded in sensor data in accordance with users'
privacy preferences and maintaining high recognition performance with limited labeled samples. This paper proposes a technique for user-controllable
privacy through feature disentanglement-based representation learning at the granular level for dynamic
privacy filtering. We also compare the efficacy of our technique against few-shot HAR using autoencoder-based representation learning. We analyze their architectural designs, learning objectives,
privacy guarantees, data efficiency, and suitability for edge Internet of Things (IoT) deployment. Our study shows that CFD-based HAR provides explicit, tunable
privacy protection controls by separating activity and sensitive attributes in the latent space, whereas autoencoder-based few-shot HAR offers superior label efficiency and lightweight adaptability but lacks inherent
privacy safeguards. We further examine the security implications of both approaches in continual IoT settings, highlighting differences in susceptibility to representation leakage and
embedding-level attacks. The analysis reveals that neither paradigm alone fully satisfies the emerging requirements of next-generation IoT HAR systems. We conclude by outlining research directions toward unified frameworks that jointly optimize
privacy preservation, few-shot adaptability, and robustness for trustworthy IoT intelligence.
Read the full abstract ▾
All authors Alex Gn, Fan Li, S Kuniyilh, Ada Axan
Machine Learning · Cross-listed from cs.CV
Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices
Rambod Azimi, Yuri Grinberg, Dan-Xia Xu et al. (+1 more)
Silicon photonic devices often exhibit fabrication-induced variations such as over-etching, underetching, and corner rounding, which can significantly alter device performance. These variations are non-uniform and are influenced by feature size and shape. Accurate digital twins are therefore needed to predict the range of possible fabricated outcomes for a given design. In this paper, we introduce Gen-Fab, a conditional generative
adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes. The proposed method takes a design layout (in GDS format) as input and produces diverse high-resolution predictions similar to scanning electron microscope (SEM) images of fabricated devices, capturing the range of process variations at the nanometer scale. To enable one-to-many mapping, we inject a latent noise vector at the model bottleneck. We compare Gen-Fab against three baselines: (1) a deterministic U-Net predictor, (2) an inference-time Monte Carlo Dropout U-Net, and (3) an ensemble of varied U-Nets. Evaluations on an out-of-distribution
dataset of fabricated photonic test structures demonstrate that Gen-Fab outperforms all baselines in both accuracy and uncertainty modeling. An additional distribution shift analysis further confirms its strong generalization to unseen fabrication geometries. Gen-Fab achieves the highest intersection-over-union (IoU) score of 89.8%, outperforming the deterministic U-Net (85.3%), the MC-Dropout U-Net (83.4%), and varying U-Nets (85.8%). It also better aligns with the distribution of real fabrication outcomes, achieving lower Kullback-Leibler divergence and Wasserstein distance.
Read the full abstract ▾
All authors Rambod Azimi, Yuri Grinberg, Dan-Xia Xu, Odile Liboiron-Ladouceur
Machine Learning
LongFlow: Efficient KV Cache Compression for Reasoning Models
Yi Su, Zhenxu Tian, Dan Qiao et al. (+3 more)
Recent
reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical
reasoning and code generation. However, this performance gain comes with substantially longer output sequences, leading to significantly increased deployment costs. In particular, long outputs require large KV caches, resulting in high
memory consumption and severe bandwidth pressure during
attention computation. Most existing KV cache optimization methods are designed for long-input, short-output scenarios and are ineffective for the long-output setting of
reasoning models. Moreover, importance estimation in prior work is computationally expensive and becomes prohibitive when continuous re-evaluation is required during long generation. To address these challenges, we propose LongFlow, a KV cache compression method with an efficient importance estimation metric derived from an intermediate result of
attention computation using only the current query. This design introduces negligible computational overhead and requires no auxiliary storage. We further develop a custom kernel that fuses FlashAttention, importance estimation, and
token eviction into a single optimized operator, improving system-level efficiency. Experiments show that LongFlow achieves up to an 11.8 times throughput improvement with 80% KV cache compression with minimal impact on model accuracy.
Read the full abstract ▾
All authors Yi Su, Zhenxu Tian, Dan Qiao, Yuechi Zhou, Juntao Li, Min Zhang
Machine Learning
Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation
Fengyuan Yu, Xiaohua Feng, Yuyuan Li et al. (+3 more)
Federated recommender systems enable collaborative model training while keeping user interaction data local and sharing only essential model parameters, thereby mitigating
privacy risks. However, existing methods overlook a critical issue, i.e., the stable learning of a generalized item
embedding throughout the
federated recommender system training process. Item
embedding plays a central role in facilitating knowledge sharing across clients. Yet, under the cross-device setting, local data distributions exhibit significant heterogeneity and sparsity, exacerbating the difficulty of learning generalized
embeddings. These factors make the stable learning of generalized item
embeddings both indispensable for effective
federated recommendation and inherently difficult to achieve. To fill this gap, we propose a new
federated recommendation framework, named
Federated Recommendation with Generalized
Embedding Learning (FedRecGEL). We reformulate the
federated recommendation problem from an item-centered perspective and cast it as a multi-task learning problem, aiming to learn generalized
embeddings throughout the training procedure. Based on theoretical analysis, we employ sharpness-aware minimization to address the generalization problem, thereby stabilizing the training process and enhancing recommendation performance. Extensive experiments on four
datasets demonstrate the effectiveness of FedRecGEL in significantly improving
federated recommendation performance. Our code is available at https://github.com/anonymifish/FedRecGEL.
Read the full abstract ▾
All authors Fengyuan Yu, Xiaohua Feng, Yuyuan Li, Changwang Zhang, Jun Wang, Chaochao Chen
Machine Learning
KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
Qizhi Chen, Chao Qi, Yihong Huang et al. (+5 more)
Graph-based
Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large
Language Model (LLM) generations. However, this reliance on external data introduces new attack surfaces. Attackers can inject poisoned texts into databases to manipulate LLMs into producing harmful target responses for attacker-chosen queries. Existing research primarily focuses on attacking conventional RAG systems. However, such methods are ineffective against GraphRAG. This robustness derives from the KG abstraction of GraphRAG, which reorganizes injected text into a graph before
retrieval, thereby enabling the LLM to reason based on the restructured context instead of raw poisoned passages. To expose latent security vulnerabilities in GraphRAG, we propose Knowledge
Evolution Poison (KEPo), a novel poisoning attack method specifically designed for GraphRAG. For each target query, KEPo first generates a toxic event containing poisoned knowledge based on the target answer. By fabricating event backgrounds and forging knowledge
evolution paths from original facts to the toxic event, it then poisons the KG and misleads the LLM into treating the poisoned knowledge as the final result. In multi-target attack scenarios, KEPo further connects multiple attack corpora, enabling their poisoned knowledge to mutually reinforce while expanding the scale of poisoned communities, thereby amplifying attack effectiveness. Experimental results across multiple
datasets demonstrate that KEPo achieves state-of-the-art attack success rates for both single-target and multi-target attacks, significantly outperforming previous methods.
Read the full abstract ▾
All authors Qizhi Chen, Chao Qi, Yihong Huang, Muquan Li, Rongzheng Wang, Dongyang Zhang, Ke Qin, Shuang Liang