Stochastic Methods

Generalization of noisy SGD in unbounded non-convex settings ICML 2025 Graph-accelerated Markov Chain Monte Carlo using Approximate Samples JMLR 2025 Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions ICML 2025 HA/TCP: A Reliable and Scalable Framework for TCP Network Functions NSDI 2025 Hazard Function Guided Agent-Based Models: A Case Study of Return Migration from Poland to Ukraine IJCAI 2025 Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations AAAI 2025 How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor? IJCNLP 2025 Hyperparametric Robust and Dynamic Influence Maximization AAAI 2025 Implicit Diffusion: Efficient optimization through stochastic sampling AISTATS 2025 Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization ICML 2025 Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling ICML 2025 Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging ICML 2025 Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems ICML 2025 Integrating Inference and Experimental Design for Contextual Behavioral Model Learning AAAI 2025 KIT’s Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization ACL 2025 Langevin Monte Carlo Beyond Lipschitz Gradient Continuity AAAI 2025 Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management AAAI 2025 Learning Robust Neural Processes with Risk-Averse Stochastic Optimization ICML 2025 Length Controlled Generation for Black-box LLMs ACL 2025 Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation CoRL 2025 Linear Bandits on Ellipsoids: Minimax Optimal Algorithms COLT 2025 Linear Streaming Bandit: Regret Minimization and Fixed-Budget Epsilon-Best Arm Identification AAAI 2025 LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression ICLR 2025 Losing Momentum in Continuous-time Stochastic Optimisation JMLR 2025 Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality (Extended Abstract) COLT 2025