← Optimization & Theory
Machine Learning › Optimization & Theory ›

Stochastic Methods

1077 directly classified papers

Papers per year

Papers

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel NIPS 2023
Bandit Task Assignment with Unknown Processing Time NIPS 2023
Decentralized Learning: Theoretical Optimality and Practical Improvements JMLR 2023
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023
KrADagrad: Kronecker approximation-domination gradient preconditioned stochastic optimization UAI 2023
Fast Heterogeneous Federated Learning with Hybrid Client Selection UAI 2023
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling ICML 2023
InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generation EMNLP 2023
Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality JMLR 2023
Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization NIPS 2023
Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach NIPS 2023
Fast Rates in Time-Varying Strongly Monotone Games ICML 2023
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks NIPS 2023
Approximate Stein Classes for Truncated Density Estimation ICML 2023
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts ICML 2023
Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability ICML 2023
Knowledge Distillation Performs Partial Variance Reduction NIPS 2023
Online Local Differential Private Quantile Inference via Self-normalization ICML 2023
Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting ICML 2023
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits ICML 2023
Learning Unnormalized Statistical Models via Compositional Optimization ICML 2023
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning ICML 2023
Efficient preconditioned stochastic gradient descent for estimation in latent variable models ICML 2023
On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm ICML 2023
SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023