Stochastic Methods

MedBN: Robust Test-Time Adaptation against Malicious Test Samples CVPR 2024 Memory-Efficient LLM Training with Online Subspace Descent NeurIPS 2024 Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning WACV 2024 Mixed-Effects Contextual Bandits AAAI 2024 Monte Carlo Tree Search in the Presence of Transition Uncertainty AAAI 2024 Multiobjective Lipschitz Bandits under Lexicographic Ordering AAAI 2024 Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses AISTATS 2024 Near-optimal Per-Action Regret Bounds for Sleeping Bandits AISTATS 2024 Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD NeurIPS 2024 Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset NeurIPS 2024 Oja's Algorithm for Streaming Sparse PCA NeurIPS 2024 On cyclical MCMC sampling AISTATS 2024 On Divergence Measures for Training GFlowNets NeurIPS 2024 On Inference Stability for Diffusion Models AAAI 2024 Online Learning of Decision Trees with Thompson Sampling AISTATS 2024 Online multiple testing with e-values AISTATS 2024 Online Sensitivity Optimization in Differentially Private Learning AAAI 2024 Online Subloop Search via Uncertainty Quantization for Efficient Test-Time Adaptation Interspeech 2024 On the Computational Complexity of Metropolis-Adjusted Langevin Algorithms for Bayesian Posterior Sampling JMLR 2024 On the Role of Server Momentum in Federated Learning AAAI 2024 On Unbiased Estimation for Partially Observed Diffusions JMLR 2024 OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations NeurIPS 2024 Optimal Scaling for the Proximal Langevin Algorithm in High Dimensions JMLR 2024 Ordered Momentum for Asynchronous SGD NeurIPS 2024 OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments AAAI 2024