Pith. sign in

REVIEW 1 cited by

On Model Stability as a Function of Random Seed

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 1909.10447 v1 pith:H5RGAMW7 submitted 2019-09-23 cs.LG cs.CLcs.NEstat.ML

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

In this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of the model in general. We specifically perform a controlled study on the effect of random seeds on the behaviour of attention, gradient-based and surrogate model based (LIME) interpretations. Our analysis suggests that random seeds can adversely affect the consistency of models resulting in counterfactual interpretations. We propose a technique called Aggressive Stochastic Weight Averaging (ASWA)and an extension called Norm-filtered Aggressive Stochastic Weight Averaging (NASWA) which improves the stability of models over random seeds. With our ASWA and NASWA based optimization, we are able to improve the robustness of the original model, on average reducing the standard deviation of the model's performance by 72%.

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. Full citation record

  1. Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Perceptually initializing a CLIP vision encoder with NIGHTS triplet judgments before YFCC15M contrastive training improves zero-shot accuracy and retrieval over an identical random-start baseline.

Pith tools