Robuta

https://openreview.net/forum?id=Vbm5UCaYeh Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards | OpenReview This paper investigates the problem of generalized linear bandits with heavy-tailed rewards, whose $(1+\epsilon)$-th moment is bounded for some $\epsilon\in... heavy tailedefficientalgorithmsgeneralizedlinear https://openreview.net/forum?id=hzlsBtfKZ1 Large Deviations and Metastability Analysis for Heavy-Tailed Dynamical Systems | OpenReview We study large deviations and metastability of heavy-tailed stochastic dynamical systems and provide the heavy-tailed counterparts of the classical... large deviationsheavy taileddynamical systemsmetastabilityanalysis https://arxiv.org/html/2410.13849v1 From Gradient Clipping to Normalization for Heavy Tailed SGD heavy tailedgradientclippingnormalizationsgd https://www.unive.it/data/agenda/9/115884 Evento: Polar depth and anomaly detection in heavy tailed data - Unive anomaly detectionheavy tailedeventopolardepth https://openreview.net/forum?id=HvLbOMgIax Efficient Distributed Optimization under Heavy-Tailed Noise | OpenReview Distributed optimization is essential for scaling modern machine learning, yet communication overhead remains a challenge. Local updates reduce this cost but... heavy tailedefficientdistributedoptimizationnoise https://openreview.net/forum?id=C6PiH9Fkjd&referrer=%5Bthe%20profile%20of%20Fabian%20Schaipp%5D(%2Fprofile%3Fid%3D~Fabian_Schaipp1) Robust gradient estimation in the presence of heavy-tailed noise | OpenReview In applications such as training transformers on NLP tasks, or distributed learning in the presence of corrupted nodes, the stochastic gradients have a... in theheavy tailedrobustgradientestimation https://openreview.net/forum?id=eR7PrfJe9o Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach | OpenReview We characterise the learning of a mixture of two clouds of data points with generic centroids via empirical risk minimisation in the high dimensional regime,... heavy tailed https://openreview.net/forum?id=TG4fKjfvxC Low-rank Matrix Bandits with Heavy-tailed Rewards | OpenReview In stochastic low-rank matrix bandit, the expected reward of an arm is equal to the inner product between its feature matrix and some unknown $d_1$ by $d_2$... rank matrixheavy tailedlowbanditsrewards https://openreview.net/forum?id=iJkskCUl2f High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality |... We investigate the high-dimensional properties of robust regression estimators in the presence of heavy-tailed contamination of both the covariates and... high dimensionalrobust regressionheavy tailed https://www.unive.it/data/33113/9/115884 Event: Polar depth and anomaly detection in heavy tailed data - Unive anomaly detectionheavy tailedeventpolardepth https://openreview.net/forum?id=TLO3pOHCyx Neural network compression with heavy-tailed SGD | OpenReview Neural network compression has been an increasingly important subject, due to its practical implications in terms of reducing the computational requirements... neural networkheavy tailedcompressionsgdopenreview https://neurips.cc/virtual/2020/public/poster_607bc9ebe4abfcd65181bfbef6252830.html NeurIPS 2020 : Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards multi armed bandits https://www.bankofcanada.ca/2026/03/staff-working-paper-2026-8/?theme_mode=light Estimation and Inference for Stochastic Volatility Models with Heavy-Tailed Distributions - Bank of... Statistical inference--both estimation and testing--for stochastic volatility (SV) models is known to be challenging and computationally demanding. We propose... https://arxiv.org/abs/2206.01095v1 [2206.01095v1] Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise Abstract page for arXiv paper 2206.01095v1: Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise stochastic methods https://arxiv.org/abs/2510.11676v1 [2510.11676v1] Accelerated stochastic first-order method for convex optimization under heavy-tailed... Abstract page for arXiv paper 2510.11676v1: Accelerated stochastic first-order method for convex optimization under heavy-tailed noise first order method https://openreview.net/forum?id=T56j6aV8Oc Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models |... Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key... https://openreview.net/forum?id=h1FhXVM0cB Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise |... In this work, we study the convergence in high probability of clipped gradient methods when the noise distribution has heavy tails, i.e., with bounded $p$th... https://www.unsw.edu.au/science/our-schools/maths/engage-with-us/seminars/2014/largest-eigenvalues-sample-covariance-matrix-p-variate-time-series-length-n-heavy Big n, Big p: Eigenvalues for Cov Matrices of Heavy-Tailed Multivariate Time Series | School of... https://www.jmlr.org/papers/v26/24-1991.html Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise:... https://deepai.org/publication/dimension-free-bounds-for-sum-of-dependent-matrices-and-operators-with-heavy-tailed-distribution Dimension-free Bounds for Sum of Dependent Matrices and Operators with Heavy-Tailed Distribution |... Oct 18, 2022 - 10/18/22 - We study the deviation inequality for a sum of high-dimensional random matrices and operators with dependence and arbitrary heavy ...