# Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"

Source: [Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"](<https://www.sota2.com/research/paper/68fa68f41e209131cea1f458>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:49:52.437Z

Authors: Jonathan Frankle

Published: 2020-12-12T20:01:33.000Z

## Abstract

We revisit and extend the experiments of Goodfellow et al. (2014), who showed that - for then state-of-the-art networks - "the objective function has a simple, approximately convex shape" along the linear path between initialization and the trained weights. We do not find this to be the case for modern networks on CIFAR-10 and ImageNet. Instead, although loss is roughly monotonically non-increasing along this path, it remains high until close to the optimum. In addition, training quickly becomes linearly separated from the optimum by loss barriers. We conclude that, although Goodfellow et al.'s findings describe the "relatively easy to optimize" MNIST setting, behavior is qualitatively different in modern settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.06898>)

[PDF](<https://arxiv.org/pdf/2012.06898.pdf>)