Stochastic Methods

Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination NeurIPS 2023 Efficient preconditioned stochastic gradient descent for estimation in latent variable models ICML 2023 Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation EMNLP 2023 EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only ACL 2023 Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule ICML 2023 Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers AAAI 2023 Faster federated optimization under second-order similarity ICLR 2023 Faster Rates of Convergence to Stationary Points in Differentially Private Optimization ICML 2023 Faster Relative Entropy Coding with Greedy Rejection Coding NeurIPS 2023 Fast Heterogeneous Federated Learning with Hybrid Client Selection UAI 2023 Fast Rates in Time-Varying Strongly Monotone Games ICML 2023 Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency EMNLP 2023 Flexible Budgets in Restless Bandits: A Primal-Dual Algorithm for Efficient Budget Allocation AAAI 2023 Fully-Adaptive Composition in Differential Privacy ICML 2023 Gradient-Free Kernel Stein Discrepancy NeurIPS 2023 Graph-Aided Online Multi-Kernel Learning JMLR 2023 HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent AISTATS 2023 High Probability Bounds for Stochastic Continuous Submodular Maximization AISTATS 2023 HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation JMLR 2023 Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise NeurIPS 2023 Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data NeurIPS 2023 InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generation EMNLP 2023 Integer Subspace Differential Privacy AAAI 2023 Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality JMLR 2023 Knowledge Distillation Performs Partial Variance Reduction NeurIPS 2023