stochastic optimization

Stochastic optimization under time drift: iterate averaging, step-decay schedules, and high probability guarantees NeurIPS 2021 Stochastic Proximal AUC Maximization JMLR 2021 Stochastic Proximal Methods for Non-Smooth Non-Convex Constrained Sparse Optimization JMLR 2021 SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients NeurIPS 2021 Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning NeurIPS 2021 The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NeurIPS 2021 The Power of Adaptivity for Stochastic Submodular Cover ICML 2021 The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization ACML 2021 Three Operator Splitting with a Nonconvex Loss Function ICML 2021 Tight sampling and discarding bounds for scenario programs with an arbitrary number of removed samples L4DC 2021 Training a Single Bandit Arm AISTATS 2021 USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems NeurIPS 2021 XOR-SGD: provable convex stochastic optimization for decision-making under uncertainty UAI 2021 Accelerated Stochastic Gradient-free and Projection-free Methods ICML 2020 Achieving Fairness in the Stochastic Multi-Armed Bandit Problem AAAI 2020 AdaGrad stepsizes: Sharp convergence over nonconvex landscapes JMLR 2020 Adam with Bandit Sampling for Deep Learning NeurIPS 2020 Adaptive Online Estimation of Piecewise Polynomial Trends NeurIPS 2020 Adaptive Sampling for Estimating Probability Distributions ICML 2020 Adaptive Sampling for Stochastic Risk-Averse Learning NeurIPS 2020 Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization NeurIPS 2020 A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning AISTATS 2020 A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control L4DC 2020 Almost Tune-Free Variance Reduction ICML 2020 Amortized variance reduction for doubly stochastic objective UAI 2020