Stochastic Methods

The Correlation-assisted Missing Data Estimator JMLR 2022 The Dynamics of Riemannian Robbins-Monro Algorithms COLT 2022 The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance COLT 2022 Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022 Toward More Effective Human Evaluation for Machine Translation ACL 2022 Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise AISTATS 2022 Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent ICML 2022 Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration JMLR 2022 Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions NeurIPS 2022 Truncated proposals for scalable and hassle-free simulation-based inference NeurIPS 2022 Truncation Sampling as Language Model Desmoothing EMNLP 2022 Trustworthy Monte Carlo NeurIPS 2022 Understanding Stochastic Optimization Behavior at the Layer Update Level (Student Abstract) AAAI 2022 A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning ICLR 2021 Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction ICLR 2021 Accelerating Distributed SGD for Linear Regression using Iterative Pre-Conditioning L4DC 2021 Adversarial Robustness of Streaming Algorithms through Importance Sampling NeurIPS 2021 A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization ICML 2021 AI-Assisted Scientific Data Collection with Iterative Human Feedback AAAI 2021 (Almost) Free Incentivized Exploration from Decentralized Learning Agents NeurIPS 2021 Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball COLT 2021 An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte Carlo AISTATS 2021 Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels NeurIPS 2021 Approximating a Distribution Using Weight Queries ICML 2021 ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021