SGD with shuffling: optimal rates without component convexity and large epoch requirements
暂无分享,去创建一个
[1] H. Robbins. A Stochastic Approximation Method , 1951 .
[2] Ohad Shamir,et al. How Good is SGD with Random Shuffling? , 2019, COLT 2019.
[3] Prateek Jain,et al. SGD without Replacement: Sharper Rates for General Smooth Convex Functions , 2019, ICML.
[4] V. Fabian. Stochastic Approximation of Minima with Improved Asymptotic Speed , 1967 .
[5] J. Kiefer,et al. Stochastic Estimation of the Maximum of a Regression Function , 1952 .
[6] Paul Tseng,et al. An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule , 1998, SIAM J. Optim..
[7] Odalric-Ambrym Maillard,et al. Concentration inequalities for sampling without replacement , 2013, 1309.4029.
[8] Albert R. Meyer,et al. Mathematics for Computer Science , 2017 .
[9] B. Recht,et al. Beneath the valley of the noncommutative arithmetic-geometric mean inequality: conjectures, case-studies, and consequences , 2012, 1202.4184.
[10] Marten van Dijk,et al. A Unified Convergence Analysis for Shuffling-Type Gradient Methods , 2020, ArXiv.
[11] Asuman E. Ozdaglar,et al. Why random reshuffling beats stochastic gradient descent , 2015, Mathematical Programming.
[12] Ohad Shamir,et al. Without-Replacement Sampling for Stochastic Gradient Methods , 2016, NIPS.
[13] D. Bertsekas,et al. Convergen e Rate of In remental Subgradient Algorithms , 2000 .
[14] Markus Schneider. Probability Inequalities for Kernel Embeddings in Sampling without Replacement , 2016, AISTATS.
[15] Dimitris Papailiopoulos,et al. Closing the convergence gap of SGD without replacement , 2020, ICML.
[16] Mark W. Schmidt,et al. Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition , 2016, ECML/PKDD.
[17] L. Bottou. Curiously Fast Convergence of some Stochastic Gradient Descent Algorithms , 2009 .
[18] Konstantin Mishchenko,et al. Random Reshuffling: Simple Analysis with Vast Improvements , 2020, NeurIPS.
[19] Suvrit Sra,et al. Random Shuffling Beats SGD after Finite Epochs , 2018, ICML.
[20] Pablo A. Parrilo,et al. Convergence Rate of Incremental Gradient and Incremental Newton Methods , 2019, SIAM J. Optim..
[21] Lek-Heng Lim,et al. Recht-Ré Noncommutative Arithmetic-Geometric Mean Conjecture is False , 2020, ICML.
[22] Léon Bottou,et al. Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.