Stochastic Methods

Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD NeurIPS 2024 Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences NeurIPS 2024 DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction NeurIPS 2024 DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction) AAAI 2024 Dynamic Spiking Graph Neural Networks AAAI 2024 Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference AAAI 2024 Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction NeurIPS 2024 Efficient Training of Language Models with Compact and Consistent Next Token Distributions ACL 2024 Ensemble sampling for linear bandits: small ensembles suffice NeurIPS 2024 Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression NeurIPS 2024 Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals NeurIPS 2024 Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption AAAI 2024 Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration NeurIPS 2024 Extragradient Type Methods for Riemannian Variational Inequality Problems AISTATS 2024 Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals AAAI 2024 Faster Differentially Private Top-k Selection: A Joint Exponential Mechanism with Pruning NeurIPS 2024 Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers ICLR 2024 Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo COLT 2024 Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization AAAI 2024 Fast two-time-scale stochastic gradient method with applications in reinforcement learning COLT 2024 FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization JMLR 2024 FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients IJCAI 2024 Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis NeurIPS 2024 f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization ICLR 2024 From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach NeurIPS 2024