Stochastic Methods

Parametric Graph for Unimodal Ranking Bandit ICML 2021 Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization ICML 2021 Principal component analysis in the stochastic differential privacy model UAI 2021 Private Adaptive Gradient Methods for Convex Optimization ICML 2021 Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning COLT 2021 Quantile Bandits for Best Arms Identification ICML 2021 Quantization Algorithms for Random Fourier Features ICML 2021 Random Coordinate Langevin Monte Carlo COLT 2021 Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems NeurIPS 2021 Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach ICML 2021 Regularising Fisher Information Improves Cross-lingual Generalisation EMNLP 2021 Robust Compressed Sensing MRI with Deep Generative Priors NeurIPS 2021 Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC AISTATS 2021 Scalable Thompson Sampling using Sparse Gaussian Process Models NeurIPS 2021 Scaling-Up Robust Gradient Descent Techniques AAAI 2021 Selective Sampling for Online Best-arm Identification NeurIPS 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality COLT 2021 SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NeurIPS 2021 SGLB: Stochastic Gradient Langevin Boosting ICML 2021 Sharper Generalization Bounds for Learning with Gradient-dominated Objective Functions ICLR 2021 Sifting through the noise: Universal first-order methods for stochastic variational inequalities NeurIPS 2021 Simple and Effective Stochastic Neural Networks AAAI 2021 Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent ACL 2021 Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning NeurIPS 2021