Machine Learning
Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions
Dmitry Yarotsky, Eugene Golikov and Yaroslav Gusev
We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation is a formal power series expansion of the loss
evolution, with coefficients encoded by diagrams akin to Feynman diagrams. We show that this expansion has a well-defined large-size limit that can be used to reveal different learning phases and, in some cases, to obtain explicit solutions of the nonlinear GF. We focus on learning Canonical Polyadic (CP) decompositions of high-order tensors, and show that this model has several distinct extreme lazy and rich GF regimes such as free
evolution, NTK and under- and over-parameterized mean-field. We show that these regimes depend on the parameter scaling, tensor order, and
symmetry of the model in a specific and subtle way. Moreover, we propose a general approach to summing the formal loss expansion by reducing it to a PDE; in a wide range of scenarios, it turns out to be first-order and solvable by the method of characteristics. We observe a very good agreement of our theoretical predictions with experimental results.
Read the full abstract ▾
Machine Learning
Continual Learning through Control Minimization
Sander de Haan, Yassine Taoudi-Benchekroun, Pau Vilimelis Aceituno et al. (+1 more)
Catastrophic forgetting remains a fundamental challenge for neural networks when tasks are trained sequentially. In this work, we reformulate continual learning as a control problem where learning and preservation signals compete within neural activity dynamics. We convert regularization penalties into preservation signals that protect prior-task representations. Learning then proceeds by minimizing the control effort required to integrate new tasks while competing with the preservation of prior tasks. At
equilibrium, the neural activities produce weight updates that implicitly encode the full prior-task
curvature, a property we term the continual-natural gradient, requiring no explicit
curvature storage. Experiments confirm that our learning framework recovers true prior-task
curvature and enables task discrimination, outperforming existing methods on standard
benchmarks without replay.
Read the full abstract ▾
All authors Sander de Haan, Yassine Taoudi-Benchekroun, Pau Vilimelis Aceituno, Benjamin F. Grewe
Machine Learning
Forget to Generalize: Iterative Adaptation for Generalization in Federated Learning
Abdulrahman Alotaibi, Irene Tenison, Miriam Kim et al. (+2 more)
The Web is naturally heterogeneous with user devices, geographic regions, browsing patterns, and contexts all leading to highly diverse, unique
datasets.
Federated Learning (FL) is an important paradigm for the Web because it enables
privacy-preserving, collaborative machine learning across diverse user devices, web services and clients without needing to centralize sensitive data. However, its performance degrades severely under non-IID client distributions that is prevalent in real-world web systems. In this work, we propose a new training paradigm - Iterative
Federated Adaptation (IFA) - that enhances generalization in heterogeneous
federated settings through generation-wise forget and evolve strategy. Specifically, we divide training into multiple generations and, at the end of each, select a fraction of model parameters (a) randomly or (b) from the later layers of the model and reinitialize them. This iterative forget and evolve schedule allows the model to escape local minima and preserve globally relevant representations. Extensive experiments on CIFAR-10, MIT-Indoors, and Stanford Dogs
datasets show that the proposed approach improves global accuracy, especially when the data cross clients are Non-IID. This method can be implemented on top any
federated algorithm to improve its generalization performance. We observe an average of 21.5%improvement across
datasets. This work advances the
vision of scalable,
privacy-preserving intelligence for real-world heterogeneous and distributed web systems.
Read the full abstract ▾
All authors Abdulrahman Alotaibi, Irene Tenison, Miriam Kim, Isaac Lee, Lalana Kagal
Machine Learning · Cross-listed from cs.CY
Learning the Value Systems of Agents with Preference-based and Inverse Reinforcement Learning
Andrés Holgado-Sánchez, Holger Billhardt, Alberto Fernández et al. (+1 more)
Agreement Technologies refer to open computer systems in which autonomous software
agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent years, it has become apparent that such agreements, in order to be acceptable to the involved parties, must remain aligned with ethical principles and moral values. However, this is notoriously difficult to ensure, especially as different human users (and their software
agents) may hold different value systems, i.e. they may differently weigh the importance of individual moral values. Furthermore, it is often hard to specify the precise meaning of a value in a particular context in a computational manner. Methods to estimate value systems based on human-engineered specifications, e.g. based on value surveys, are limited in scale due to the need for intense human moderation. In this article, we propose a novel method to automatically learn value systems from observations and human demonstrations. In particular, we propose a formal model of the value system learning problem, its instantiation to sequential decision-making domains based on multi-objective Markov decision processes, as well as tailored preference-based and inverse reinforcement learning
algorithms to infer value grounding functions and value systems. The approach is illustrated and evaluated by two simulated use cases.
Read the full abstract ▾
All authors Andrés Holgado-Sánchez, Holger Billhardt, Alberto Fernández, Sascha Ossowski
Machine Learning · Cross-listed from q-bio.NC
Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
Jan-Matthis Lueckmann, Viren Jain and Michał Januszewski
Constructing mechanistic models of neural
circuits is a fundamental goal of neuroscience, yet verifying such models is limited by the lack of ground truth. To rigorously test model discovery, we establish an in silico testbed using neuromechanical simulations of a larval zebrafish as a transparent ground truth. We find that LLM-based tree search autonomously discovers predictive models that significantly outperform established
forecasting baselines. Conditioning on sensory drive is necessary but not sufficient for faithful system identification, as models exploit statistical shortcuts. Structural priors prove essential for enabling robust out-of-distribution generalization and recovery of interpretable mechanistic models. Our insights provide guidance for modeling real-world neural recordings and offer a broader template for AI-driven scientific discovery.
Read the full abstract ▾
Machine Learning
Greedy-Gnorm: A Gradient Matrix Norm-Based Alternative to Attention Entropy for Head Pruning
Yuxi Guo and Paul Sheridan
Attention head
pruning has emerged as an effective technique for
transformer model compression, an increasingly important goal in the era of Green AI. However, existing
pruning methods often rely on static importance scores, which fail to capture the evolving role of
attention heads during iterative removal. We propose Greedy-Gradient norm (Greedy-Gnorm), a novel head
pruning algorithm that dynamically recalculates head importance after each
pruning step. Specifically, each head is scored by the elementwise product of the l2-norms of its Q/K/V gradient blocks, as estimated from a hold-out validation set and updated at every greedy iteration. This dynamic approach to scoring mitigates against stale rankings and better reflects gradient-informed importance as
pruning progresses. Extensive experiments on BERT, ALBERT, RoBERTa, and XLM-RoBERTa demonstrate that Greedy-Gnorm consistently preserves accuracy under substantial head removal, outperforming
attention entropy. By effectively reducing model size while maintaining task performance, Greedy-Gnorm offers a promising step toward more energy-efficient
transformer model deployment.
Read the full abstract ▾
Machine Learning · Cross-listed from math.ST
Universality of General Spiked Tensor Models
Yanjin Xiang and Zhihua Zhang
We study asymmetric rank-one spiked tensor models in the high-dimensional regime, where the noise entries are independent and identically distributed with zero mean, unit variance, and finite fourth moment. This extends the classical Gaussian framework to a substantially broader class of noise distributions. We analyze the maximum-likelihood
estimator associated with the best rank-one approximation of an order-$d$ tensor, for $d\ge 3$. Our approach is formulated along an informative, spectrally separated branch of stationary points of the non-convex maximum-likelihood landscape. In the core order-three asymmetric model, we verify locally in the high-signal regime that such an informative branch exists and remains separated from the bulk. Under this branch-selection framework, we show that the empirical spectral distribution of a suitable block-wise tensor contraction converges almost surely to the same deterministic limit as in the Gaussian case. As a consequence, the asymptotic singular value and the mode-wise
alignments between the estimated and planted spike directions admit the same explicit characterizations as under Gaussian noise. These results establish a universality principle for asymmetric spiked tensor models: the high-dimensional spectral behavior and statistical limits of the selected maximum-likelihood stationary point are robust beyond the Gaussian setting. Our proof combines resolvent methods from random
matrix theory, cumulant expansions under finite fourth-moment assumptions, and Efron–Stein-type variance bounds. A main technical difficulty is to control the statistical dependence between the
estimator and the noise, including the associated cross terms in the non-Gaussian setting.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Bayesian PINNs for uncertainty-aware inverse problems (BPINN-IP)
Ali Mohammad-Djafari
The main contribution of this paper is to develop a hierarchical
Bayesian formulation of PINNs for linear inverse problems, which is called BPINN-IP. The proposed methodology extends PINN to account for prior knowledge on the nature of the expected NN output, as well as its weights. Also, as we can have access to the posterior probability distributions, naturally uncertainties can be quantified. Also, variational inference and Monte Carlo dropout are employed to provide predictive means and variances for reconstructed images. Un example of applications to deconvolution and super-resolution is considered, details of the different steps of implementations are given, and some preliminary results are presented.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ME
Journey to the Centre of Cluster: Harnessing Interior Nodes for A/B Testing under Network Interference
Qianyi Chen, Anpeng Wu, Bo Li et al. (+2 more)
A/B testing on platforms often faces challenges from network interference, where a unit's outcome depends not only on its own treatment but also on the treatments of its network neighbors. To address this, cluster-level randomization has become standard, enabling the use of network-aware
estimators. These
estimators typically trim the data to retain only a subset of informative units, achieving low bias under suitable conditions but often suffering from high variance. In this paper, we first demonstrate that the interior nodes - units whose neighbors all lie within the same cluster - constitute the vast majority of the post-trimming subpopulation. In light of this, we propose directly averaging over the interior nodes to construct the mean-in-interior (MII)
estimator, which circumvents the delicate reweighting required by existing network-aware
estimators and substantially reduces variance in classical settings. However, we show that interior nodes are often not representative of the full population, particularly in terms of network-dependent
covariates, leading to notable bias. We then augment the MII
estimator with a counterfactual predictor trained on the entire network, allowing us to adjust for
covariate distribution shifts between the interior nodes and full population. By rearranging the expression, we reveal that our augmented MII
estimator embodies an analytical form of the point
estimator within prediction-powered inference framework. This insight motivates a semi-supervised lens, wherein interior nodes are treated as labeled data subject to selection bias. Extensive and challenging simulation studies demonstrate the outstanding performance of our augmented MII
estimator across various settings.
Read the full abstract ▾
All authors Qianyi Chen, Anpeng Wu, Bo Li, Lu Deng, Yong Wang
Machine Learning
Routing-Aware Safety Alignment for Mixture-of-Experts Models
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang et al. (+1 more)
Mixture-of-Experts (MoE)
language models introduce unique challenges for safety
alignment due to their sparse routing mechanisms, which can enable degenerate optimization behaviors under standard full-parameter fine-tuning. In our preliminary experiments, we observe that naively applying full-parameter safety fine-tuning to MoE models can reduce attack success rates through routing or expert dominance effects, rather than by directly repairing Safety-Critical Experts. To address this challenge, we propose RASA, a routing-aware expert-level
alignment framework that explicitly repairs Safety-Critical Experts while preventing routing-based bypasses. RASA identifies experts disproportionately activated by successful jailbreaks, selectively fine-tunes only these experts under fixed routing, and subsequently enforces routing consistency with safety-aligned contexts. Across two representative MoE architectures and a diverse set of jailbreak attacks, RASA achieves near-perfect robustness, strong cross-attack generalization, and substantially reduced over-refusal, while preserving general capabilities on
benchmarks such as MMLU, GSM8K, and TruthfulQA. Our results suggest that robust MoE safety
alignment benefits from targeted expert repair rather than global parameter updates, offering a practical and architecture-preserving alternative to prior approaches.
Read the full abstract ▾
All authors Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang
Machine Learning
Mixture of Masters: Sparse Chess Language Models with Player Routing
Giacomo Frisoni, Lorenzo Molfetta, Davide Freddi et al. (+1 more)
Modern chess
language models are dense
transformers trained on millions of games played by thousands of high-rated individuals. However, these monolithic networks tend to collapse into mode-averaged behavior, where stylistic boundaries are blurred, and rare but effective strategies are suppressed. To counteract homogenization, we introduce Mixture-of-Masters (MoM), the first chess mixture-of-experts model with small-sized GPT experts emulating world-class grandmasters. For each move, a post-hoc learnable gating network selects the most appropriate persona to channel depending on the game state, allowing MoM to switch its style dynamically, e.g., Tal's offensive vocation or Petrosian's defensive solidity. When evaluated against Stockfish on unseen standard games, MoM outperforms both dense individual expert networks and popular GPT baselines trained on aggregated data, while ensuring generation variety, control, and interpretability.
Read the full abstract ▾
All authors Giacomo Frisoni, Lorenzo Molfetta, Davide Freddi, Gianluca Moro
Machine Learning · Cross-listed from cs.CL
No One-Size-Fits-All: Building Systems For Translation to Bashkir, Kazakh, Kyrgyz, Tatar and Chuvash Using Synthetic And Original Data
Dmitry Karpov
We explore machine translation for five Turkic
language pairs: Russian-Bashkir, Russian-Kazakh, Russian-Kyrgyz, English-Tatar, English-Chuvash. Fine-tuning nllb-200-distilled-600M with LoRA on synthetic data achieved chrF++ 49.71 for Kazakh and 46.94 for Bashkir. Prompting DeepSeek-V3.2 with retrieved similar examples achieved chrF++ 39.47 for Chuvash. For Tatar, zero-shot or
retrieval-based approaches achieved chrF++ 41.6, while for Kyrgyz the zero-shot approach reached 45.6. We release the
dataset and the obtained weights.
Read the full abstract ▾
Machine Learning
Hand Gesture Recognition from Doppler Radar Signals Using Echo State Networks
Towa Sano and Gouhei Tanaka
Hand gesture recognition (HGR) is a fundamental technology in human computer interaction (HCI).In particular, HGR based on Doppler radar signals is suited for in-vehicle interfaces and robotic systems, necessitating lightweight and computationally efficient recognition techniques. However, conventional deep learning-based methods still suffer from high computational costs. To address this issue, we propose an Echo State Network (ESN) approach for radar-based HGR, using frequency-modulated-continuous-wave (FMCW) radar signals. Raw radar data is first converted into feature maps, such as range-time and Doppler-time maps, which are then fed into one or more recurrent neural network-based reservoirs. The obtained reservoir states are processed by readout classifiers, including ridge regression, support vector machines, and random forests. Comparative experiments demonstrate that our method outperforms existing approaches on an 11-class HGR task using the Soli
dataset and surpasses existing deep learning models on a 4-class HGR task using the Dop-NET
dataset. The results indicate that parallel processing using multi-reservoir ESNs are effective for recognizing temporal patterns from the multiple different feature maps in the time-space and time-frequency domains. Our ESN approaches achieve high recognition performance with low computational cost in HGR, showing great potential for more advanced HCI technologies, especially in resource-constrained environments.
Read the full abstract ▾
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Machine Learning-Driven Crystal System Prediction for Perovskites Using Augmented X-ray Diffraction Data
Ansu Mathew, Ahmer A. B. Baloch, Alamin Yakasai et al. (+3 more)
Prediction of
crystal system from X-ray diffraction (XRD) spectra is a critical task in materials science, particularly for perovskite materials which are known for their diverse applications in photovoltaics, optoelectronics, and catalysis. In this study, we present a machine learning (ML)-driven framework that leverages advanced models, including Time Series Forest (TSF), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), Long Short-Term
Memory (LSTM), Gated Recurrent Unit (GRU), and a simple feedforward neural network (NN), to classify
crystal systems, point groups, and space groups from XRD data of perovskite materials. To address class imbalance and enhance model robustness, we integrated feature augmentation strategies such as Synthetic Minority Over-sampling Technique (SMOTE), class weighting, jittering, and spectrum shifting, along with efficient data preprocessing pipelines. The TSF model with SMOTE augmentation achieved strong performance for
crystal system prediction, with a Matthews correlation coefficient (MCC) of 0.9, an F1 score of 0.92, and an accuracy of 97.76%. For point and space group prediction, balanced accuracies above 95% were obtained. The model demonstrated high performance for
symmetry-distinct classes, including cubic
crystal systems, point groups 3m and m-3m, and space groups Pnma and Pnnn. This work highlights the potential of ML for XRD-based structural characterization and accelerated discovery of perovskite materials
Read the full abstract ▾
All authors Ansu Mathew, Ahmer A. B. Baloch, Alamin Yakasai, Hemant Mittal, Vivian Alberts, Jayakumar V. Karunamurthy
Machine Learning
MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
Jonathan Nöther, Adish Singla and Goran Radanovic
LLM-based multi-
agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual
agents fail or behave adversarially. In this work, we study the automated design of agentic systems that remain safe even when a subset of
agents is compromised. Inspired by Stackelberg security games, we formalize this problem as a game between a system designer (the Meta-
Agent) and a best-responding Meta-Adversary that selects and compromises a subset of
agents to minimize safety. We propose Meta-Adversary-Meta-
Agent (MaMa), a novel
algorithm inspired by this formalization for automatically designing safe agentic systems. Our approach uses LLM-based
adversarial search, where the Meta-
Agent iteratively proposes system designs and receives feedback based on the strongest attacks discovered by the Meta-Adversary. Empirical evaluations across diverse environments show that systems designed with MaMa consistently defend against worst-case attacks while maintaining performance comparable to systems optimized solely for task success. Moreover, the resulting systems generalize to stronger adversaries, as well as ones with different attack objectives or underlying LLMs, demonstrating robust safety beyond the training setting.
Read the full abstract ▾
Machine Learning
EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL
Lunjun Zhang and Jimmy Ba
Reinforcement Learning (RL) has enabled Large
Language Models (LLMs) to acquire increasingly complex
reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient
algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-k KL
estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for using EMA anchor; moreover, we show that our Top-k KL
estimator yields both unbiased KL values and unbiased gradients at any k, while bringing the benefits of exact KL. When combined with GRPO, the two techniques (EMA-PG) lead to a significant performance boost. On math
reasoning, it allows R1-distilled Qwen-1.5B to reach 53.9% on OlympiadBench compared to 50.8% by GRPO. On agentic RL domains, with Qwen-3B base, EMA-PG improves GRPO by an average of 33.3% across 7
datasets of Q&A with search engines, including 29.7% $\rightarrow$ 44.1% on HotpotQA, 27.4% $\rightarrow$ 40.1% on 2WikiMultiHopQA. Overall, we show that EMA-PG is a simple, principled, and powerful approach to scaling RL for LLMs. Code: https://github.com/LunjunZhang/ema-pg
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation
Puyue Wang, Jiawei Hu, Yan Gao et al. (+7 more)
Humanoid robots can suffer significant performance drops under small changes in dynamics, task specifications, or environment setup. We propose HoRD, a two-stage learning framework for robust
humanoid control under domain shift. First, we train a high-performance teacher policy via history-conditioned reinforcement learning, where the policy infers latent dynamics context from recent state–action trajectories to adapt online to diverse randomized dynamics. Second, we perform online
distillation to transfer the teacher's robust control capabilities into a
transformer-based student policy that operates on sparse root-relative 3D joint keypoint trajectories. By combining history-conditioned adaptation with online
distillation, HoRD enables a single policy to adapt zero-shot to unseen domains without per-domain retraining. Extensive experiments show HoRD outperforms strong baselines in robustness and transfer, especially under unseen domains and external perturbations. Code and project page are available at https://tonywang-0517.github.io/hord/.
Read the full abstract ▾
All authors Puyue Wang, Jiawei Hu, Yan Gao, Junyan Wang, Yu Zhang, Gillian Dobbie, Tao Gu, Wafa Johal, Ting Dang, Hong Jia
Machine Learning
Separation-Utility Pareto Frontier: An Information-Theoretic Characterization
Shizhou Xu
We study the Pareto frontier (optimal trade-off) between utility and separation, a
fairness criterion requiring predictive independence from sensitive attributes conditional on the true outcome. Through an information-theoretic lens, we prove a characterization of the utility-separation Pareto frontier, establish its concavity, and thereby prove the increasing marginal cost of separation in terms of utility. In addition, we characterize the conditions under which this trade-off becomes strict, providing a guide for trade-off selection in practice. Based on the theoretical characterization, we develop an empirical regularizer based on conditional mutual information (CMI) between predictions and sensitive attributes given the true outcome. The CMI regularizer is compatible with any deep model trained via gradient-based optimization and serves as a scalar monitor of residual separation violations, offering tractable guarantees during training. Finally, numerical experiments support our theoretical findings: across COMPAS, UCI Adult, UCI Bank, and CelebA, the proposed method substantially reduces separation violations while matching or exceeding the utility of established baseline methods. This study thus offers a provable, stable, and flexible approach to enforcing separation in deep learning.
Read the full abstract ▾
Machine Learning
Theory of Speciation Transitions in Diffusion Models with General Class Structure
Beatrice Achilli, Marco Benedetti, Giulio Biroli et al. (+1 more)
Diffusion Models generate data by reversing a
stochastic diffusion process, progressively transforming noise into structured samples drawn from a target distribution. Recent theoretical work has shown that this backward dynamics can undergo sharp qualitative transitions, known as speciation transitions, during which trajectories become dynamically committed to data classes. Existing theoretical analyses, however, are limited to settings where classes are identifiable through first moments, such as mixtures of Gaussians with well-separated means. In this work, we develop a general theory of speciation in
diffusion models that applies to arbitrary target distributions admitting well-defined classes. We formalize the notion of class structure through Bayes classification and characterize speciation times in terms of free-
entropy difference between classes. This criterion recovers known results in previously studied Gaussian-mixture models, while extending to situations in which classes are not distinguishable by first moments and may instead differ through higher-order or collective features. Our framework also accommodates multiple classes and predicts the existence of successive speciation times associated with increasingly fine-grained class commitment. We illustrate the theory on two analytically tractable examples: mixtures of one-dimensional Ising models at different temperatures and mixtures of zero-mean Gaussians with distinct covariance structures. In the Ising case, we obtain explicit expressions for speciation times by mapping the problem onto a random-field Ising model and solving it via the replica method. Our results provide a unified and broadly applicable description of speciation transitions in
diffusion-based generative models.
Read the full abstract ▾
All authors Beatrice Achilli, Marco Benedetti, Giulio Biroli, Marc Mézard
Machine Learning · Cross-listed from stat.ML
Performative Learning Theory
Julian Rodemann, Unai Fischer-Abaigar, James Bailie et al. (+1 more)
Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app's predictions? We address this question by
embedding performative predictions into statistical learning theory. We prove generalization bounds under performative effects on the sample, on the population, and on both. A key intuition behind our proofs is that in the worst case, the population negates predictions, while the sample deceptively fulfills them. We cast such self-negating and self-fulfilling predictions as min-max and min-min risk functionals in Wasserstein space, respectively. Our analysis reveals a fundamental trade-off between performatively changing the world and learning from it: the more a model affects data, the less it can learn from it. Moreover, our analysis results in a surprising insight on how to improve generalization guarantees by retraining on performatively distorted samples. We illustrate our bounds in a case study on prediction-informed assignments of unemployed German residents to job trainings, drawing upon administrative labor
market records from 1975 to 2017 in Germany.
Read the full abstract ▾
All authors Julian Rodemann, Unai Fischer-Abaigar, James Bailie, Krikamol Muandet
Machine Learning · Cross-listed from cs.GT
Optimal Rates for Feasible Payoff Set Estimation in Games
Annalisa Barbara, Riccardo Poiani, Martino Bernasconi et al. (+1 more)
We study a setting in which two players play a (possibly approximate) Nash
equilibrium of a bimatrix game, while a learner observes only their actions and has no knowledge of the
equilibrium or the underlying game. A natural question is whether the learner can rationalize the observed behavior by inferring the players' payoff functions. Rather than producing a single payoff estimate, inverse game theory aims to identify the entire set of payoffs consistent with observed behavior, enabling downstream use in, e.g., counterfactual analysis and mechanism design across applications like auctions, pricing, and security games. We focus on the problem of estimating the set of feasible payoffs with high probability and up to precision $\epsilon$ on the Hausdorff metric. We provide the first minimax-optimal rates for both exact and approximate
equilibrium play, in zero-sum as well as general-sum games. Our results provide learning-theoretic foundations for set-valued payoff inference in multi-
agent environments.
Read the full abstract ▾
All authors Annalisa Barbara, Riccardo Poiani, Martino Bernasconi, Andrea Celli
Machine Learning
LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
Andrej Jovanović, Alex Iacob, Mher Safaryan et al. (+6 more)
Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the
memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-
hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in
language modeling and downstream tasks at model scales of $125$M–$720$M, while reducing communication by $\approx 10 \times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-
memory settings with small rank/batch size.
Read the full abstract ▾
All authors Andrej Jovanović, Alex Iacob, Mher Safaryan, Ionut-Vlad Modoranu, Lorenzo Sani, William F. Shen, Xinchi Qiu, Dan Alistarh, Nicholas D. Lane
Machine Learning
On the use of LLMs to generate a dataset of Neural Networks
Nadia Daoudi and Jordi Cabot
Neural networks are increasingly used to support decision-making. To verify their reliability and adaptability, researchers and practitioners have proposed a variety of tools and methods for tasks such as NN code verification, refactoring, and migration. These tools play a crucial role in guaranteeing both the correctness and maintainability of neural network architectures, helping to prevent implementation errors, simplify model updates, and ensure that complex networks can be reliably extended and reused. Yet, assessing their effectiveness remains challenging due to the lack of publicly diverse
datasets of neural networks that would allow systematic evaluation. To address this gap, we leverage large
language models (LLMs) to automatically generate a
dataset of neural networks that can serve as a
benchmark for validation. The
dataset is designed to cover diverse architectural components and to handle multiple input data types and tasks. In total, 608 samples are generated, each conforming to a set of precise design choices. To further ensure their consistency, we validate the correctness of the generated networks using static analysis and symbolic tracing. We make the
dataset publicly available to support the community in advancing research on neural network reliability and adaptability.
Read the full abstract ▾
Machine Learning
Blockchain Federated Learning for Sustainable Retail: Reducing Waste through Collaborative Demand Forecasting
Fabio Turazza, Alessandro Neri, Marcello Pietri et al. (+3 more)
Effective demand
forecasting is crucial for reducing food waste. However, data
privacy concerns often hinder collaboration among retailers, limiting the potential for improved predictive accuracy. In this study, we explore the application of
Federated Learning (FL) in Sustainable Supply Chain Management (SSCM), with a focus on the grocery retail sector dealing with perishable goods. We develop a baseline predictive model for demand
forecasting and waste assessment in an isolated retailer scenario. Subsequently, we introduce a Blockchain-based FL model, trained collaboratively across multiple retailers without direct data sharing. Our preliminary results show that FL models have performance almost equivalent to the ideal setting in which parties share data with each other, and are notably superior to models built by individual parties without sharing data, cutting waste and boosting efficiency.
Read the full abstract ▾
All authors Fabio Turazza, Alessandro Neri, Marcello Pietri, Maria Angela Butturi, Marco Picone, Marco Mamei
Machine Learning
Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
Rui Yuan, Mykola Khandoga and Vinay Kumar Sankarapu
Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical
reasoning and code generation tasks. Despite extensive exploration of reward processing strategies and training dynamics, all existing group-based methods exclusively use KL divergence for policy regularization, leaving the choice of divergence function unexplored. We introduce Group-Based Mirror Policy Optimization (GBMPO), a framework that extends group-based policy optimization to flexible Bregman divergences, including hand-designed alternatives (L2 in probability space) and learned neural mirror maps. On GSM8K mathematical
reasoning, hand-designed ProbL2-GRPO achieves 86.7% accuracy, improving +5.5 points over the Dr. GRPO baseline. On MBPP code generation, neural mirror maps reach 60.1-60.8% pass@1, with random initialization already capturing most of the benefit. While evolutionary strategies meta-learning provides marginal accuracy improvements, its primary value lies in variance reduction ($\pm$0.2 versus $\pm$0.6) and efficiency gains (15% shorter responses on MBPP), suggesting that random initialization of neural mirror maps is sufficient for most practical applications. These results establish divergence choice as a critical, previously unexplored design dimension in group-based policy optimization for LLM
reasoning.
Read the full abstract ▾
Machine Learning
Reducing the labeling burden in time-series mapping using Common Ground: a semi-automated approach to tracking changes in land cover and species over time
Geethen Singh, Jasper A Slingsby, Tamara B Robinson et al. (+1 more)
Reliable classification of Earth Observation data depends on consistent, up-to-date reference labels. However, collecting new labelled data at each time step remains expensive and logistically difficult, especially in dynamic or remote ecological systems. As a response to this challenge, we demonstrate that a model with access to reference data solely from time step t0 can perform competitively on both t0 and a future time step t1, outperforming models trained separately on time-specific reference data (the gold standard). This finding suggests that effective temporal generalization can be achieved without requiring manual updates to reference labels beyond the initial time step t0. Drawing on concepts from change detection and semi-supervised learning (SSL), the most performant approach, "Common Ground", uses a semi-supervised framework that leverages temporally stable regions-areas with little to no change in spectral or semantic characteristics between time steps-as a source of implicit supervision for dynamic regions. We evaluate this strategy across multiple classifiers, sensors (Landsat-8, Sentinel-2 satellite multispectral and airborne imaging spectroscopy), and ecological use cases. For invasive tree species mapping, we observed a 21-40% improvement in classification accuracy using Common Ground compared to naive temporal transfer, where models trained at a single time step are directly applied to a future time step. We also observe a 10 -16% higher accuracy for the introduced approach compared to a gold-standard approach. In contrast, when broad land cover categories were mapped across Europe, we observed a more modest 2% increase in accuracy compared to both the naive and gold-standard approaches. These results underscore the effectiveness of combining stable reference screening with SSL for scalable and label-efficient multi-temporal remote sensing classification.
Read the full abstract ▾
All authors Geethen Singh, Jasper A Slingsby, Tamara B Robinson, Glenn Moncrieff
Machine Learning
Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis
Zongjiang Shang, Dongliang Cui, Binqing Wu et al. (+1 more)
Recently, there has been great success in leveraging pre-trained large
language models (LLMs) for time series analysis. The core idea lies in effectively aligning the modality between natural
language and time series. However, the multi-scale structures of natural
language and time series have not been fully considered, resulting in insufficient utilization of LLMs capabilities. To this end, we propose MSH-LLM, a Multi-Scale Hypergraph method that aligns Large
Language Models for time series analysis. Specifically, a hyperedging mechanism is designed to enhance the multi-scale semantic information of time series semantic space. Then, a cross-modality
alignment (CMA) module is introduced to align the modality between natural
language and time series at different scales. In addition, a mixture of
prompts (MoP) mechanism is introduced to provide contextual information and enhance the ability of LLMs to understand the multi-scale temporal patterns of time series. Experimental results on 27 real-world
datasets across 5 different applications demonstrate that MSH-LLM achieves the state-of-the-art results.
Read the full abstract ▾
All authors Zongjiang Shang, Dongliang Cui, Binqing Wu, Ling Chen
Machine Learning
EXaMCaP: Subset Selection with Entropy Gain Maximization for Probing Capability Gains of Large Chart Understanding Training Sets
Jiapeng Liu, Liang Li, Bing Li et al. (+5 more)
Recent works focus on synthesizing Chart Understanding (ChartU) training sets to inject advanced chart knowledge into
Multimodal Large
Language Models (MLLMs), where the sufficiency of the knowledge is typically verified by quantifying capability gains via the fine-tune-then-evaluate paradigm. However, full-set fine-tuning MLLMs to assess such gains incurs significant time costs, hindering the iterative refinement cycles of the ChartU
dataset. Reviewing the ChartU
dataset synthesis and data selection domains, we find that subsets can potentially probe the MLLMs' capability gains from full-set fine-tuning. Given that data diversity is vital for boosting MLLMs' performance and
entropy reflects this feature, we propose EXaMCaP, which uses
entropy gain maximization to select a subset. To obtain a high-diversity subset, EXaMCaP chooses the maximum-
entropy subset from the large ChartU
dataset. As enumerating all possible subsets is impractical, EXaMCaP iteratively selects samples to maximize the gain in set
entropy relative to the current set, approximating the maximum-
entropy subset of the full
dataset. Experiments show that EXaMCaP outperforms baselines in probing the capability gains of the ChartU training set, along with its strong effectiveness across diverse subset sizes and compatibility with various MLLM architectures.
Read the full abstract ▾
All authors Jiapeng Liu, Liang Li, Bing Li, Peng Fu, Xiyan Gao, Chengyang Fang, Xiaoshuai Hao, Can Ma
Machine Learning · Cross-listed from stat.ML
Anytime-Valid Conformal Risk Control
Bror Hultberg, Dave Zachariah and Antônio H. Ribeiro
Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration
datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively growing calibration
dataset at any time point. We derive such guarantees using
quantile-based arguments and illustrate the applicability of the proposed framework to settings involving distribution shift. We further establish a matching lower bound and show that our guarantees are asymptotically tight. Finally, we demonstrate the practical performance of our methods through both simulations and real-world numerical examples.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
Zekun Li, Ning Wang, Tongxin Bai et al. (+4 more)
Visual AutoRegressive (VAR) modeling has garnered significant
attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all
tokens across historical scales at each autoregressive step. As the next scale resolution grows, the computational complexity of
attention increases quartically with resolution, causing substantial latency. Prior accelerations often skip high-resolution scales, which speeds up inference but discards high-frequency details and harms image quality. To address these problems, we present SparVAR, a training-free acceleration framework that exploits three properties of VAR
attention: (i) strong
attention sinks, (ii) cross-scale activation similarity, and (iii) pronounced locality. Specifically, we dynamically predict the sparse
attention pattern of later high-resolution scales from a sparse decision scale, and construct scale self-similar sparse
attention via an efficient index-mapping mechanism, enabling high-efficiency sparse
attention computation at large scales. Furthermore, we propose cross-scale local sparse
attention and implement an efficient block-wise sparse kernel, which achieves $\mathbf{> 5\times}$ faster forward speed than FlashAttention. Extensive experiments demonstrate that the proposed SparVAR can reduce the generation time of an 8B model producing $1024\times1024$ high-resolution images to the 1s, without skipping the last scales. Compared with the VAR baseline accelerated by FlashAttention, our method achieves a $\mathbf{1.57\times}$ speed-up while preserving almost all high-frequency details. When combined with existing scale-skipping strategies, SparVAR attains up to a $\mathbf{2.28\times}$ acceleration, while maintaining competitive visual generation quality. Code is available at \href{https://github.com/CAS-CLab/SparVAR}{SparVAR}.
Read the full abstract ▾
All authors Zekun Li, Ning Wang, Tongxin Bai, Changwang Mei, Peisong Wang, Shuang Qiu, Jian Cheng