LossPlot: A Better Way to Visualize Loss Landscapes
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
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
- 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
- 2018Essentially No Barriers in Neural Network Energy Landscapecited by 328
- 2014Qualitatively characterizing neural network optimization problemscited by 186
- 2014A survey of dimensionality reduction techniquescited by 50
- 2017Direct-Manipulation Visualization of Deep Networkscited by 26
- 2019Loss Patterns of Neural Networkscited by 10
Built on by
Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 1; 2025: 1.
5 papers.
- 2022Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environmentscited by 9
- 2024Deep Loss Convexification for Learning Iterative Modelscited by 3
- 2021Visualizing the Loss Landscape of Winning Lottery Ticketscited by 2
- 2022FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networkscited by 2
- 2025ChannelExplorer: Exploring Class Separability Through Activation Channel Visualizationcited by 1
- 2025ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization6 May 2025
- 2024Deep Loss Convexification for Learning Iterative Models16 Nov 2024
- 2022Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments14 May 2022
- 2022FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks9 Apr 2022
- 2021Visualizing the Loss Landscape of Winning Lottery Tickets16 Dec 2021