linear convergence

Convergence of Continual Learning in Homogeneous Deep Networks COLT 2026 Quantized Stochastic Primal–Dual Methods for Distributed Optimization under Relaxed Global Geometry UAI 2026 Subgradient Method for System Identification with Non-Smooth Objectives L4DC 2026 φ-Update: A Class of Policy Update Methods with Policy Convergence Guarantee ICLR 2025 Beyond Discretization: Learning the Optimal Solution Path AISTATS 2025 Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs ICLR 2025 Learning Mixtures of Experts with EM: A Mirror Descent Perspective ICML 2025 Linear convergence of Sinkhorn’s algorithm for generalized static Schrödinger bridge ICML 2025 Linear Trading Position with Sparse Spectrum IJCAI 2025 LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently ICML 2025 On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms ICML 2025 On the Convergence of Tâtonnement for Linear Fisher Markets AAAI 2025 Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients JMLR 2025 Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization NeurIPS 2024 Convergence of log(1/ε) for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis NeurIPS 2024 DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations AAAI 2024 Distributionally Robust Optimization with Bias and Variance Reduction ICLR 2024 Error bounds, PL condition, and quadratic growth for weakly convex functions, and linear convergences of proximal point methods L4DC 2024 Fundamental Benefit of Alternating Updates in Minimax Optimization ICML 2024 How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization ICLR 2024 Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence NeurIPS 2024 Large-Scale Gaussian Processes via Alternating Projection AISTATS 2024 No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths ICML 2024 On the Hyperparameters in Stochastic Gradient Descent with Momentum JMLR 2024 Policy Mirror Descent with Lookahead NeurIPS 2024