arXiv Machine Learning June 8, 2026 By Qianqian Lei, Soham Bonnerjee, Yuefeng Han, Wei Biao Wu

Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments

Read the original on arXiv Machine Learning →

arXiv:2606. 06855v1 Announce Type: cross Abstract: While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or sub-Gaussian/sub-Weibull tail assumptions, which can be overly restrictive for modern settings with heavy-tailed or unbounded losses.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 4

Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards

arXiv:2604. 10727v2 Announce Type: replace-cross Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gaussian losses but can be ineffective when losses or rewards are heavy-tailed.

By Huiming Zhang, Binghan Li, Wan Tian, Qiang Sun

llms reinforcement-learning safety

arXiv Machine Learning

Jun 4

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

arXiv:2602. 05657v2 Announce Type: replace Abstract: The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm.

By Aleksandar Armacki, Dragana Bajovi\'c, Du\v{s}an Jakoveti\'c, Soummya Kar, Ali H. Sayed

arXiv AI

Jun 4

Does Order Matter : Connecting The Law of Robustness to Robust Generalization

arXiv:2602. 20971v3 Announce Type: replace-cross Abstract: Bubeck and Selke (2021) propose the connection between the Law of Robustness and robust generalization error as an open problem.

By Mihir More, Aritra Das, Jaee Ponde, Himadri Mandal, Vishnu Varadarajan, Debayan Gupta

arXiv Machine Learning

Jun 2

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise

arXiv:2606. 00520v1 Announce Type: cross Abstract: Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite $p$-th moment for $p\in\left(1,2\right)$, a setting known as the heavy-tailed noise assumption.

By Zijian Liu

arXiv Machine Learning

Aug 3

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

arXiv:2605. 26000v2 Announce Type: replace-cross Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization.

By Jose Blanchet, Peter Glynn, Wenhao Yang

arXiv Machine Learning

Aug 11

Kernel Methods for Refined Prophet Inequalities

arXiv:2608. 08662v1 Announce Type: cross Abstract: The single-selection prophet inequality is a canonical Bayesian online selection problem in which independent nonnegative values arrive sequentially and the decision-maker must irrevocably select at most one.

By Patrick Loiseau, Mathieu Molina, Vianney Perchet, Sebastian Perez-Salazar, Victor Verdugo

benchmarks

Related stories

Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

Does Order Matter : Connecting The Law of Robustness to Robust Generalization

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

Kernel Methods for Refined Prophet Inequalities