SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.07160 · 2023

Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
garywei944/grab-sampler pwc_unofficial 2 of 2
FunctionStatusWhere it lives
pretty_time Ran garywei944/grab-sampler/src/grabsampler/utils/EventTimer.py
code served (permissive licence) · get_code("1d7531c00408358b")
probabilistic_balance Ran garywei944/grab-sampler/src/grabsampler/sorter/SorterBase.py
code served (permissive licence) · get_code("54406a3eec6d5938")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We study convergence lower bounds of without-replacement stochastic gradient descent (SGD) for solving smooth (strongly-)convex finite-sum minimization problems. Unlike most existing results focusing on final iterate lower bounds in terms of the number of components $n$ and the number of epochs $K$, we seek bounds for arbitrary weighted average iterates that are tight in all factors including the condition number $κ$. For SGD with Random Reshuffling, we present lower bounds that have tighter $κ$ dependencies than existing bounds. Our results are the first to perfectly close the gap between lower and upper bounds for weighted average iterates in both strongly-convex and convex cases. We also prove weighted average iterate lower bounds for arbitrary permutation-based SGD, which apply to all variants that carefully choose the best permutation. Our bounds improve the existing bounds in factors of $n$ and $κ$ and thereby match the upper bounds shown for a recently proposed algorithm called GraB.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.07160")
get_code_for_paper("2303.07160")
have("2303.07160")

Connect an agent — have() is free.