mlsanityData to 7 Oct 2026

LossPlot: A Better Way to Visualize Loss Landscapes

arXiv 2111.15133 ↗First posted 30 Nov 2021cs.LG cs.CV cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

8 of 12 references.

References · 8

  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  2. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  3. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  4. 2018Essentially No Barriers in Neural Network Energy Landscapecited by 328
  5. 2014Qualitatively characterizing neural network optimization problemscited by 186
  6. 2014A survey of dimensionality reduction techniquescited by 50
  7. 2017Direct-Manipulation Visualization of Deep Networkscited by 26
  8. 2019Loss Patterns of Neural Networkscited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 1; 2025: 1.

5 papers.