stochastic gradient descent

Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent JMLR 2026 Stochastic Gradient Methods: Bias, Stability and Generalization JMLR 2026 Suspicious Alignment of SGD:A Fine-Grained Step Size Condition Analysis ALT 2026 Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization COLT 2026 Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract) COLT 2026 Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization UAI 2026 AdaGK-SGD: Adaptive Global Knowledge Guided Distributed Stochastic Gradient Descent AAAI 2025 Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models ICLR 2025 Almost Sure Convergence of Dropout Algorithms for Neural Networks JMLR 2025 Analyzing the Role of Permutation Invariance in Linear Mode Connectivity AISTATS 2025 Approximating Metric Magnitude of Point Sets AAAI 2025 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 Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning JMLR 2025 Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness ICLR 2025 Correlated Quantization for Faster Nonconvex Distributed Optimization UAI 2025 Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent AAAI 2025 Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions ICML 2025 Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization AISTATS 2025 Do Deep Neural Network Solutions Form a Star Domain? ICLR 2025 Does SGD really happen in tiny subspaces? ICLR 2025 Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism ICLR 2025 EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback JMLR 2025 Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025 Explicit and Implicit Graduated Optimization in Deep Neural Networks AAAI 2025