AI Chat AI Image Generator AI Video Text to Speech

LossPlot: A Better Way to Visualize Loss Landscapes

11/30/2021

∙

by Robert Bain, et al.

∙

∙

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.

Robert Bain
4 publications
Mikhail Tokarev
1 publication
Harsh Kothari
1 publication
Rahul Damineni
1 publication

page 2

page 4

research

∙ 07/28/2023

How regularization affects the geometry of loss functions

What neural networks learn depends fundamentally on the geometry of the ...

0 Nathaniel Bottman, et al. ∙

research

∙ 10/28/2022

Evaluating the Impact of Loss Function Variation in Deep Learning for Classification

The loss function is arguably among the most important hyperparameters f...

0 Simon Dräger, et al. ∙

research

∙ 10/27/2018

A New Loss Function for Temperature Scaling to have Better Calibrated Deep Networks

However Deep neural networks recently have achieved impressive results f...

0 Azadeh Sadat Mozafari, et al. ∙

research

∙ 03/29/2023

Lipschitzness Effect of a Loss Function on Generalization Performance of Deep Neural Networks Trained by Adam and AdamW Optimizers

The generalization performance of deep neural networks with regard to th...

0 Mohammad Lashkari, et al. ∙

research

∙ 11/29/2018

Tuplemax Loss for Language Identification

In many scenarios of a language identification task, the user will speci...

0 Li Wan, et al. ∙

research

∙ 07/21/2021

Memorization in Deep Neural Networks: Does the Loss Function matter?

Deep Neural Networks, often owing to the overparameterization, are shown...

0 Deep Patel, et al. ∙

research

∙ 12/31/2020

Blade Envelopes Part II: Multiple Objectives and Inverse Design

Blade envelopes offer a set of data-driven tolerance guidelines for manu...

0 Chun Yui Wong, et al. ∙