Papers › Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

1 Dec 2020NeurIPS 2020 12archive 2025-07-28

Ankit Pensia, Shashank Rajput, Alliot Nagle, Harit Vishwakarma, Dimitris Papailiopoulos

The strong lottery ticket hypothesis (LTH) postulates that one can approximate any target neural network by only pruning the weights of a sufficiently over-parameterized random network. A recent work by Malach et al. [MYSS20] establishes the first theoretical analysis for the strong LTH: one can provably approximate a neural network of width d and depth l, by pruning a random one that is a factor O(d⁴ l²) wider and twice as deep. This polynomial over-parameterization requirement is at odds with recent experimental research that achieves good approximation with networks that are a small factor wider than the target. In this work, we close the gap and offer an exponential improvement to the over-parameterization requirement for the existence of lottery tickets. We show that any target network of width d and depth l can be approximated by pruning a random network that is a factor O(log(dl)) wider and twice as deep. Our analysis heavily relies on connecting pruning random ReLU networks to random instances of the Subset Sum problem. We then show that this logarithmic over-parameterization is essentially optimal for constant depth networks. Finally, we verify several of our theoretical insights with experiments.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

acnagle/optimal-lottery-tickets officialpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient (arXiv:2006.07990; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PruningReLU

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections