Pith. sign in

REVIEW 1 cited by

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.01067 v4 pith:W733LI2R submitted 2019-05-03 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords lotterynetworksperformanceweightsmodelnetworkresultssigns
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recent "Lottery Ticket Hypothesis" paper by Frankle & Carbin showed that a simple approach to creating sparse networks (keeping the large weights) results in models that are trainable from scratch, but only when starting from the same initial weights. The performance of these networks often exceeds the performance of the non-sparse base model, but for reasons that were not well understood. In this paper we study the three critical components of the Lottery Ticket (LT) algorithm, showing that each may be varied significantly without impacting the overall results. Ablating these factors leads to new insights for why LT networks perform as well as they do. We show why setting weights to zero is important, how signs are all you need to make the reinitialized network train, and why masking behaves like training. Finally, we discover the existence of Supermasks, masks that can be applied to an untrained, randomly initialized network to produce a model with performance far better than chance (86% on MNIST, 41% on CIFAR-10).

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 107 citations worldwide. Full citation record

  1. An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures

    cs.CV 2025-09 conditional novelty 5.0 of 10

    Freezing the first four blocks or the whole backbone of YOLOv8/YOLOv10 can match or beat full fine-tuning while using less GPU memory, but aggressive freezing fails on heavily augmented single-class data.

Pith tools