Pith. sign in

REVIEW 1 cited by

LossPlot: A Better Way to Visualize Loss Landscapes

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2111.15133 v1 pith:O3PH7VOW submitted 2021-11-30 cs.LG cs.CVcs.HC

Robert Bain , Mikhail Tokarev , Harsh Kothari , Rahul Damineni This is my paper · ORCID
classification cs.LGcs.CVcs.HC
keywords losslandscapeslossplototherabilityacceptsallowsapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Investigations into the loss landscapes of deep neural networks are often laborious. This work documents our user-driven approach to create a platform for semi-automating this process. LossPlot accepts data in the form of a csv, and allows multiple trained minimizers of the loss function to be manipulated in sync. Other features include a simple yet intuitive checkbox UI, summary statistics, and the ability to control clipping which other methods do not offer.

Discussion (0). Continue with ORCID 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. Deep Loss Convexification for Learning Iterative Models

    cs.CV 2024-11 conditional novelty 5.0 of 10

    Adding star-convexity hinge losses during training makes a model's loss landscape bowl-shaped around the ground truth and improves iterative predictions on RNN, point cloud registration, and image alignment tasks.

Pith tools