Stochastic Methods

Beyond Discretization: Learning the Optimal Solution Path AISTATS 2025 Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum using Increasing Batch Size ACML 2025 Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025 Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions ICLR 2025 Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025 Long-time asymptotics of noisy SVGD outside the population limit ICLR 2025 Self-Evolutionary Large Language Models Through Uncertainty-Enhanced Preference Optimization AAAI 2025 Exact Mean Square Linear Stability Analysis for SGD COLT 2024 Gradient-based Discrete Sampling with Automatic Cyclical Scheduling NeurIPS 2024 Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024 Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent NeurIPS 2024 Post-Hoc Reversal: Are We Selecting Models Prematurely? NeurIPS 2024 QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation NeurIPS 2024 Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference NeurIPS 2024 Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction AAAI 2024 Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective NeurIPS 2024 ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization AAAI 2024 A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution ICLR 2023 A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. ICLR 2023 Differentially Private Learning with Per-Sample Adaptive Clipping AAAI 2023 Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond NeurIPS 2023 Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks AAAI 2023 Learning Compact Features via In-Training Representation Alignment AAAI 2023 Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent NeurIPS 2023 Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling JMLR 2022