Stochastic Methods

Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning ICML 2023 Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD COLT 2023 Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise COLT 2023 Buffered Asynchronous SGD for Byzantine Learning JMLR 2023 Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting ICML 2023 Byzantine-Tolerant Methods for Distributed Variational Inequalities NeurIPS 2023 Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity AISTATS 2023 Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023 Combating Mode Collapse via Offline Manifold Entropy Estimation AAAI 2023 Communication-Efficient Stochastic Gradient Descent Ascent with Momentum Algorithms IJCAI 2023 Controllable Text Generation via Probability Density Estimation in the Latent Space ACL 2023 Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023 Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data ICML 2023 Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction NeurIPS 2023 Decentralized Learning: Theoretical Optimality and Practical Improvements JMLR 2023 Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization NeurIPS 2023 Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel NeurIPS 2023 Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap COLT 2023 DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models EMNLP 2023 Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning ICML 2023 Distributed Stochastic Nested Optimization for Emerging Machine Learning Models: Algorithm and Theory AAAI 2023 Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction ICML 2023 Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models NeurIPS 2023 Doubly Robust Stein-Kernelized Monte Carlo Estimator: Simultaneous Bias-Variance Reduction and Supercanonical Convergence JMLR 2023 Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards NeurIPS 2023