← Optimization & Theory
Machine Learning › Optimization & Theory ›

Stochastic Methods

1077 directly classified papers

Papers per year

Papers

Online Multi-Armed Bandits with Adaptive Inference NIPS 2021
Explicit Regularization of Stochastic Gradient Methods through Duality AISTATS 2021
(Almost) Free Incentivized Exploration from Decentralized Learning Agents NIPS 2021
Optimal Underdamped Langevin MCMC Method NIPS 2021
Stochastic Anderson Mixing for Nonconvex Stochastic Optimization NIPS 2021
Time-independent Generalization Bounds for SGLD in Non-convex Settings NIPS 2021
Efficient Sampling of Dependency Structure EMNLP 2021
Online stochastic gradient descent on non-convex losses from high-dimensional inference JMLR 2021
Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent ACL 2021
Loop Estimator for Discounted Values in Markov Reward Processes AAAI 2021
Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration AAAI 2021
Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs NIPS 2021
The Implicit Bias of Minima Stability: A View from Function Space NIPS 2021
Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions NIPS 2021
Last iterate convergence of SGD for Least-Squares in the Interpolation regime. NIPS 2021
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021
Sifting through the noise: Universal first-order methods for stochastic variational inequalities NIPS 2021
Multiplicative Noise and Heavy Tails in Stochastic Optimization ICML 2021
On Proximal Policy Optimization’s Heavy-tailed Gradients ICML 2021
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021
Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data ICML 2021
One-pass Stochastic Gradient Descent in overparametrized two-layer neural networks AISTATS 2021
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information NIPS 2021
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization ICML 2021
Evaluating the Implicit Midpoint Integrator for Riemannian Hamiltonian Monte Carlo ICML 2021