conftrace_
← Optimization & Theory
Deep Learning › Optimization & Theory ›

Stochastic Methods

97 papers

Papers per year

1
6
9
3
'10
'15
'20
'25

Papers

Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025
Self-Evolutionary Large Language Models Through Uncertainty-Enhanced Preference Optimization AAAI 2025
Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling NIPS 2024
Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective NIPS 2024
QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation NIPS 2024
Post-Hoc Reversal: Are We Selecting Models Prematurely? NIPS 2024
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent NIPS 2024
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference NIPS 2024
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization AAAI 2024
Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction AAAI 2024
Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024
Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond NIPS 2023
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent NIPS 2023
Learning Compact Features via In-Training Representation Alignment AAAI 2023
Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks AAAI 2023
Differentially Private Learning with Per-Sample Adaptive Clipping AAAI 2023
The alignment property of SGD noise and how it helps select flat minima: A stability analysis NIPS 2022
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms NIPS 2022
Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NIPS 2022
On the Theoretical Properties of Noise Correlation in Stochastic Optimization NIPS 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NIPS 2022
Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization NIPS 2022
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent NIPS 2022
Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization NIPS 2022