Stochastic Methods

KrADagrad: Kronecker approximation-domination gradient preconditioned stochastic optimization UAI 2023 Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards NeurIPS 2023 Large deviations rates for stochastic gradient descent with strongly convex functions AISTATS 2023 Learning-augmented count-min sketches via Bayesian nonparametrics JMLR 2023 Learning Unnormalized Statistical Models via Compositional Optimization ICML 2023 Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single ICML 2023 MixFlows: principled variational inference via mixed flows ICML 2023 Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions ICML 2023 Multi-Fidelity Multi-Armed Bandits Revisited NeurIPS 2023 Online Local Differential Private Quantile Inference via Self-normalization ICML 2023 Online robust non-stationary estimation NeurIPS 2023 Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval JMLR 2023 On Robustness of Finetuned Transformer-based NLP Models EMNLP 2023 On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm ICML 2023 On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms NeurIPS 2023 On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data CVPR 2023 On Universal Portfolios with Continuous Side Information AISTATS 2023 Optimal Execution via Multi-Objective Multi-Armed Bandits (Student Abstract) AAAI 2023 Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits ICML 2023 PDPP:Projected Diffusion for Procedure Planning in Instructional Videos CVPR 2023 Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference ICML 2023 Practical Differentially Private Hyperparameter Tuning with Subsampling NeurIPS 2023 Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima NeurIPS 2023 Predictor-corrector algorithms for stochastic optimization under gradual distribution shift ICLR 2023 Predict-then-Calibrate: A New Perspective of Robust Contextual LP NeurIPS 2023