Stochastic Methods

Convergence of Langevin Monte Carlo in Chi-Squared and Rényi Divergence AISTATS 2022 Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022 Convex Analysis of the Mean Field Langevin Dynamics AISTATS 2022 Coordinating Momenta for Cross-Silo Federated Learning AAAI 2022 Data-Driven Conditional Robust Optimization NeurIPS 2022 Decentralized Local Stochastic Extra-Gradient for Variational Inequalities NeurIPS 2022 De-Sequentialized Monte Carlo: a parallel-in-time particle smoother JMLR 2022 Detached Error Feedback for Distributed SGD with Random Sparsification ICML 2022 Dimension-free convergence rates for gradient Langevin dynamics in RKHS COLT 2022 Distributed Stochastic Nash Equilibrium Learning in Locally Coupled Network Games with Unknown Parameters L4DC 2022 Distribution Compression in Near-Linear Time ICLR 2022 Doubly Sparse Asynchronous Learning for Stochastic Composite Optimization IJCAI 2022 Dynamic Pricing with Monotonicity Constraint under Unknown Parametric Demand Model NeurIPS 2022 Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution NeurIPS 2022 Efficiency Ordering of Stochastic Gradient Descent NeurIPS 2022 Efficient Submodular Optimization under Noise: Local Search is Robust NeurIPS 2022 Efficient Variance Reduction for Meta-learning ICML 2022 Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning NeurIPS 2022 Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability NeurIPS 2022 Faster Stochastic Algorithms for Minimax Optimization under Polyak-{\L}ojasiewicz Condition NeurIPS 2022 Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NeurIPS 2022 Fourier Learning with Cyclical Data ICML 2022 Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits ICLR 2022 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 Gaussian Process Parameter Estimation Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits JMLR 2022