Stochastic Methods

Super-Fibonacci Spirals: Fast, Low-Discrepancy Sampling of SO(3) CVPR 2022 Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology ICML 2022 The AIM and EM Algorithms for Learning from Coarse Data JMLR 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 The Dynamics of Riemannian Robbins-Monro Algorithms COLT 2022 The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization NeurIPS 2022 The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning ICML 2022 The Mirror Langevin Algorithm Converges with Vanishing Bias ALT 2022 The Perils of Learning Before Optimizing AAAI 2022 The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation ICML 2022 The power of first-order smooth optimization for black-box non-smooth problems ICML 2022 The query complexity of sampling from strongly log-concave distributions in one dimension COLT 2022 The Semi-random Likelihood of Doctrinal Paradoxes AAAI 2022 The Two-Sided Game of Googol JMLR 2022 Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization NeurIPS 2022 Three rates of convergence or separation via U-statistics in a dependent framework JMLR 2022 Thresholded Lasso Bandit ICML 2022 Tight and Robust Private Mean Estimation with Few Users ICML 2022 Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints NeurIPS 2022 Toward Physically Realizable Quantum Neural Networks AAAI 2022 Towards An Efficient Approach for the Nonconvex lp Ball Projection: Algorithm and Analysis JMLR 2022 Towards a Theory of Non-Log-Concave Sampling:First-Order Stationarity Guarantees for Langevin Monte Carlo COLT 2022 Towards Fully Sparse Training: Information Restoration with Spatial Similarity AAAI 2022 Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration JMLR 2022 Trajectory Inference via Mean-field Langevin in Path Space NeurIPS 2022