Variance

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 70

All topics

Softmax gradient policy for variance minimization and risk-averse multi armed bandits
Mar 31, 2026Gabriel TuriniciStochastic Multi-Armed Bandits Variance Reduction
CEREMADE, Université Paris Dauphine - PSL, CNRS, Paris, France
When Does Sparsity Mitigate the Curse of Depth in LLMs
Mar 16, 2026Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta +4Sparsity Layer-Wise
Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen · Tübingen AI Center +4
Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Bound
Mar 6, 2026Hangyi ZhaoRegret Long-Tailed Distribution
Stable Velocity: A Variance Perspective on Flow Matching
Feb 5, 2026Donglin Yang, Yongxing Zhang, Xin Yu +5Contrastive Flow Matching Accelerated Sampling
University of Hong Kong, Hong Kong · University of British Columbia, Canada · Vector Institute for AI, Toronto, Canada +2
Dual Randomized Smoothing: Beyond Global Noise Variance
Dec 1, 2025Chenhao Sun, Yuhao Mao, Martin VechevSmoothing Noise-Aware
Department of Computer Science, ETH Zürich, Switzerland
Measuring Intent Comprehension in LLMs
Jun 19, 2025Nadav Kunievsky, James A. EvansVariance
Knowlesdge Lab, University of Chicago, Chicago, Illinois, USA · Knowledge Lab, Data Science Institute, Department of Sociology, University of Chicago, Chicago, Illinois, USA.
An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
Apr 25, 2025Christopher Bülte, Yusuf Sale, Timo Löhr +3Uncertainty Quantification Uncertainty
1LMU Munich · 2Munich Center for Machine Learning (MCML) · 3DLR-German Aerospace Center +2
Towards Weaker Variance Assumptions for Stochastic Optimization
Apr 14, 2025Ahmet Alacaoglu, Yura Malitsky, Stephen J. WrightStochastic Convex Optimization Stochastic Optimization
Department of Mathematics, University of British Columbia · Faculty of Mathematics, University of Vienna · Department of Computer Sciences, University of Wisconsin–Madison
Statistical Taylor Expansion: A New and Path-Independent Method for Uncertainty Analysis
Oct 2, 2024Chengpu WangInput Uncertainties Variance
Grossman Street, Melville, NY 11747, USA
Variance Reduction for Independent Metropolis
Jun 25, 2024Siran Liu, Petros Dellaportas, Michalis K. TitsiasVariance Reduction Variance
Department of Statistical Science, University College London, UK. · Department of Statistics, Athens University of Economics and Business, Greece. · Google DeepMind, UK.

Mar 31, 2026, cs.LGJ/K move · Enter open · S save

Softmax gradient policy for variance minimization and risk-averse multi armed bandits

Gabriel Turinici

CEREMADE, Université Paris Dauphine - PSL, CNRS, Paris, France

Stochastic Multi-Armed Bandits Variance Reduction Sequential Decision Making Variance Activation Functions

Open paper AskPDF arXiv

Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and numerically. While most classical approaches aim to identify the arm with the highest expected reward, we focus on a risk-aware setting where the goal is to select the arm with the lowest variance, favoring stability over potentially high but uncertain returns. To model the decision process, we consider a softmax parameterization of the policy; we propose a new algorithm to select the minimal variance (or minimal risk) arm and prove its convergence under natural conditions. The algorithm constructs an unbiased estimate of the objective by using two independent draws from the selected arm's distribution. We provide numerical experiments that illustrate the practical behavior of these algorithms and offer guidance on implementation choices. The setting also covers general risk-aware problems where there is a trade-off between maximizing the average reward and minimizing its variance.

Momentum

Related topics

Latest papers 70