Overview

The field asks how to estimate, optimize, and make predictions when noise has only a finite p-th moment, or occasionally infinite variance. Common approaches include clipping and truncation, Huber losses, median-of-means estimators, and robust variants of SGD, mirror descent, and bandit algorithms. These methods are studied in settings such as nonconvex optimization, time-series and system identification, federated learning, and stochastic bandits, with guarantees expressed in terms of tail moments and dependence. A central tension is that robustness can control rare large errors but may add bias or slow convergence, while methods that adapt to unknown tail behavior can have unavoidable performance costs.

Latest papers

CardsList

34 papers0 papers in the last four weeks, down 100% on the four weeks before. 0.0% of all new papers.

  1. Heavy-Tailed and Long-Range Dependent Noise in Stochastic Approximation: A Finite-Time Analysis

    Mar 20, 2026Siddharth Chandak, Anuj Yadav, Ayfer Ozgur +1Stochastic ApproximationStochastic Optimization Convergence

  2. Asynchronous Heavy-Tailed Optimization

    Feb 20, 2026Junfei Sun, Dixi Yao, Xuchen Gong +3Stochastic OptimizationHeavy-Tailed Stochastic Optimization

  3. Accelerated stochastic first-order method for convex optimization under heavy-tailed noise

    Oct 13, 2025Chuan He, Bowen Li, Zhaosong LuStochastic OptimizationHeavy-Tailed Noise

  4. Batched Bandits with Heavy-Tailed Rewards

    Oct 4, 2025Yunwen Guo, Yunlun Shu, Gongyi Zhuo +1Lipschitz BanditsMulti-Armed Bandits