Stochastic Methods

From Past to Future: Rethinking Eligibility Traces AAAI 2024 Fully Unconstrained Online Learning NeurIPS 2024 GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework AAAI 2024 Gaussian Cooling and Dikin Walks: The Interior-Point Method for Logconcave Sampling COLT 2024 General Tail Bounds for Non-Smooth Stochastic Mirror Descent AISTATS 2024 Global Rewards in Restless Multi-Armed Bandits NeurIPS 2024 Gradient-based Discrete Sampling with Automatic Cyclical Scheduling NeurIPS 2024 Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm JMLR 2024 Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models NeurIPS 2024 High Probability and Risk-Averse Guarantees for a Stochastic Accelerated Primal-Dual Method JMLR 2024 High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise JMLR 2024 iMESA: Incremental Distributed Optimization for Collaborative Simultaneous Localization and Mapping RSS 2024 Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024 Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability COLT 2024 Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes AISTATS 2024 Infinite Limits of Multi-head Transformer Dynamics NeurIPS 2024 In Search of a Data Transformation That Accelerates Neural Field Training CVPR 2024 Interaction-Force Transport Gradient Flows NeurIPS 2024 Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting ICLR 2024 Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning NeurIPS 2024 Learning Discrete-Time Major-Minor Mean Field Games AAAI 2024 Learning the Pareto Set Under Incomplete Preferences: Pure Exploration in Vector Bandits AISTATS 2024 Learning with Posterior Sampling for Revenue Management under Time-varying Demand IJCAI 2024 Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning NeurIPS 2024 Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling JMLR 2024