Aiming towards the minimizers: fast convergence of SGD for
overparametrized problems

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems

5 June 2023

Dmitriy Drusvyatskiy

Papers citing "Aiming towards the minimizers: fast convergence of SGD for overparametrized problems"

13 / 13 papers shown

Title
A Novel Unified Parametric Assumption for Nonconvex Optimization Artem Riabinin Ahmed Khaled Peter Richtárik 62 0 0 17 Feb 2025
Loss Landscape Characterization of Neural Networks without Over-Parametrization Rustem Islamov Niccolò Ajroldi Antonio Orvieto Aurelien Lucchi 35 4 0 16 Oct 2024
Nesterov acceleration in benignly non-convex landscapes Kanan Gupta Stephan Wojtowytsch 36 2 0 10 Oct 2024
Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent Yen-Che Hsiao Abhishek Dutta 16 0 0 02 Aug 2024
Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning Qi Qi Quanqi Hu Qihang Lin Tianbao Yang 37 1 0 09 Jun 2024
From Inverse Optimization to Feasibility to ERM Saurabh Mishra Anant Raj Sharan Vaswani 25 2 0 27 Feb 2024
Challenges in Training PINNs: A Loss Landscape Perspective Pratik Rathore Weimu Lei Zachary Frangella Lu Lu Madeleine Udell AI4CE PINN ODL 44 39 0 02 Feb 2024
A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent Mingze Wang Lei Wu 33 3 0 01 Oct 2023
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths Charles Guille-Escuret Hiroki Naganuma Kilian Fatras Ioannis Mitliagkas 16 3 0 20 Jun 2023
How much pre-training is enough to discover a good subnetwork? Cameron R. Wolfe Fangshuo Liao Qihan Wang J. Kim Anastasios Kyrillidis 30 3 0 31 Jul 2021
Stochastic algorithms with geometric step decay converge linearly on sharp functions Damek Davis Dmitriy Drusvyatskiy Vasileios Charisopoulos 36 26 0 22 Jul 2019
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 139 1,199 0 16 Aug 2016
Learning without Concentration S. Mendelson 85 333 0 01 Jan 2014