Robuta

https://openreview.net/forum?id=SqGn6phAxR&referrer=%5Bthe%20profile%20of%20Zhuo%20Sun%5D(%2Fprofile%3Fid%3D~Zhuo_Sun1) Meta-learning Control Variates: Variance Reduction with Limited Data | OpenReview Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates can be challenging when... meta learningcontrol variatesvariance reductionlimited dataopenreview https://deepai.org/publication/sgd-with-variance-reduction-beyond-empirical-risk-minimization SGD with Variance Reduction beyond Empirical Risk Minimization | DeepAI Oct 16, 2015 - 10/16/15 - We introduce a doubly stochastic proximal gradient algorithm for optimizing a finite average of smooth convex functions, whose gra... empirical risk minimizationvariance reductionsgdbeyonddeepai https://jmlr.org/papers/v25/22-1036.html Decentralized Natural Policy Gradient with Variance Reduction for Collaborative Multi-Agent... policy gradientvariance reductiondecentralizednatural https://arxiv.org/abs/2102.08352 [2102.08352] Stochastic Variance Reduction for Variational Inequality Methods Abstract page for arXiv paper 2102.08352: Stochastic Variance Reduction for Variational Inequality Methods stochastic variance reductionvariational inequality210208352methods https://openreview.net/forum?id=tmQH8prqLc Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions | OpenReview This paper explores adaptive variance reduction methods for stochastic optimization based on the STORM technique. Existing adaptive extensions of STORM rely on... variance reductionstochastic optimizationadaptiveweakerassumptions https://jmlr.org/papers/v21/19-073.html Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and... variance reductionestimatesequencesstochasticcomposite https://openreview.net/forum?id=H1tSsb-AW Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines | OpenReview Action-dependent baselines can be bias-free and yield greater variance reduction than state-only dependent baselines for policy gradient methods. variance reductionpolicy gradient https://openreview.net/forum?id=6t_dLShIUyZ Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity | OpenReview Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under... variance reduction https://openreview.net/forum?id=Syx1DkSYwB Variance Reduction With Sparse Gradients | OpenReview We use sparsity to improve the computational complexity of variance reduction methods. variance reductionsparsegradientsopenreview https://deepai.org/publication/double-clipping-less-biased-variance-reduction-in-off-policy-evaluation Double Clipping: Less-Biased Variance Reduction in Off-Policy Evaluation | DeepAI variance reductionpolicy evaluationdoubleclippingless https://openreview.net/forum?id=v9Wq-mycD4r Variance Reduction in Off-Policy Deep Reinforcement Learning using Spectral Normalization |... Off-policy deep reinforcement learning algorithms like Soft Actor Critic (SAC) have achieved state-of-the-art results in several high dimensional continuous... deep reinforcement learningvariance reductionpolicy https://jmlr.org/papers/v22/20-1205.html Langevin Monte Carlo: random coordinate descent and variance reduction langevin monte carlorandom coordinate descentvariancereduction https://jmlr.org/papers/v24/21-1313.html Doubly Robust Stein-Kernelized Monte Carlo Estimator: Simultaneous Bias-Variance Reduction and... monte carlo https://www.mdpi.com/1424-8220/21/15/5124 DisSAGD: A Distributed Parameter Update Scheme Based on Variance Reduction Machine learning models often converge slowly and are unstable due to the significant variance of random data when using a sample estimate gradient in SGD. To... based ondistributedparameterupdatescheme https://arxiv.org/abs/2508.10539 [2508.10539] Improving Value-based Process Verifier via Low-Cost Variance Reduction Abstract page for arXiv paper 2508.10539: Improving Value-based Process Verifier via Low-Cost Variance Reduction value based https://arxiv.org/abs/2109.03207v1 [2109.03207v1] COCO Denoiser: Using Co-Coercivity for Variance Reduction in Stochastic Convex... Abstract page for arXiv paper 2109.03207v1: COCO Denoiser: Using Co-Coercivity for Variance Reduction in Stochastic Convex Optimization