Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods

3 February 2022

Papers citing "Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods"

13 / 13 papers shown

Title
Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees Daniil Medyakov Gleb Molodtsov Grigoriy Evseev Egor Petrov Aleksandr Beznosikov 278 3 0 04 Sep 2025
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement SamplingNeural Information Processing Systems (NeurIPS), 2024 Junyi Li Heng Huang 196 1 0 07 Nov 2024
On the Last-Iterate Convergence of Shuffling Gradient MethodsInternational Conference on Machine Learning (ICML), 2024 Zijian Liu Zhengyuan Zhou 353 8 0 12 Mar 2024
Understanding the Training Speedup from Sampling with Approximate LossesInternational Conference on Machine Learning (ICML), 2024 Rudrajit Das Xi Chen Bertram Ieong Parikshit Bansal Sujay Sanghavi 142 3 0 10 Feb 2024
Stochastic optimization with arbitrary recurrent data samplingInternational Conference on Machine Learning (ICML), 2024 William G. Powell Hanbaek Lyu 213 1 0 15 Jan 2024
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD AlgorithmsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Rustem Islamov M. Safaryan Dan Alistarh FedML 180 22 0 31 Oct 2023
On The Impact of Machine Learning Randomness on Group FairnessConference on Fairness, Accountability and Transparency (FAccT), 2023 Prakhar Ganesh Hong Chang Martin Strobel Reza Shokri FaML 192 36 0 09 Jul 2023
Ordering for Non-Replacement SGD Yuetong Xu Baharan Mirzasoleiman 117 0 0 28 Jun 2023
On Convergence of Incremental Gradient for Non-Convex Smooth FunctionsInternational Conference on Machine Learning (ICML), 2023 Anastasia Koloskova N. Doikov Sebastian U. Stich Martin Jaggi 316 5 0 30 May 2023
Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally Konstantinos E. Nikolakakis Amin Karbasi Dionysis Kalogerias 273 7 0 03 May 2023
Tighter Lower Bounds for Shuffling SGD: Random Permutations and BeyondInternational Conference on Machine Learning (ICML), 2023 Jaeyoung Cha Jaewook Lee Chulhee Yun 236 26 0 13 Mar 2023
Coordinating Distributed Example Orders for Provably Accelerated TrainingNeural Information Processing Systems (NeurIPS), 2023 A. Feder Cooper Wentao Guo Khiem Pham Tiancheng Yuan Charlie F. Ruan Yucheng Lu Chris De Sa 489 8 0 02 Feb 2023
GraB: Finding Provably Better Data Permutations than Random ReshufflingNeural Information Processing Systems (NeurIPS), 2022 Yucheng Lu Wentao Guo Christopher De Sa FedML 264 18 0 22 May 2022