Papers › On a continuous time model of gradient descent dynamics and instability in deep learning

On a continuous time model of gradient descent dynamics and instability in deep learning

3 Feb 2023arXiv:2302.01952archive 2025-07-28

Mihaela Rosca, Yan Wu, Chongli Qin, Benoit Dherin

The recipe behind the success of deep learning has been the combination of neural networks and gradient-based optimization. Understanding the behavior of gradient descent however, and particularly its instability, has lagged behind its empirical success. To add to the theoretical tools available to study gradient descent we propose the principal flow (PF), a continuous time flow that approximates gradient descent dynamics. To our knowledge, the PF is the only continuous flow that captures the divergent and oscillatory behaviors of gradient descent, including escaping local minima and saddle points. Through its dependence on the eigendecomposition of the Hessian the PF sheds light on the recently observed edge of stability phenomena in deep learning. Using our new understanding of instability we propose a learning rate adaptation method which enables us to control the trade-off between training stability and test set evaluation performance.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2302.01952")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: community (archive-listed): 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

deepmind/discretisation_drift officialmentioned in papermentioned on GitHubjaxApache-2.0 report
deepmind/dd_two_player_games mentioned on GitHubjaxApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from deepmind/dd_two_player_games. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

binary_cross_entropy_loss deepmind/dd_two_player_games/dd_two_player_games/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ee04e47cc8ffe35 · report
calculate_frechet_distance_with_error_bars deepmind/dd_two_player_games/dd_two_player_games/metric_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · d217f26096c77c6d · report
calculate_inception_score deepmind/dd_two_player_games/dd_two_player_games/metric_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 91a2171efdef64bc · report
calculate_inception_scores_with_error_bars deepmind/dd_two_player_games/dd_two_player_games/metric_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · e1191eecfa7fae5f · report
filter_out_new_training_state deepmind/dd_two_player_games/dd_two_player_games/gan.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c0abb6ad51c15e5 · report
get_player_fn deepmind/dd_two_player_games/dd_two_player_games/gan.py community (archive-listed) unverified Apache-2.0 (permissive) · 0465af73b2877578 · report
image_postprocess deepmind/dd_two_player_games/dd_two_player_games/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 960e1119c4129674 · report
image_preprocess deepmind/dd_two_player_games/dd_two_player_games/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 801251546afebbdc · report
sn_dict_for_logging deepmind/dd_two_player_games/dd_two_player_games/experiment.py community (archive-listed) unverified Apache-2.0 (permissive) · f870d8d7e9089108 · report
square_loss deepmind/dd_two_player_games/dd_two_player_games/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · f63e9d5b08ab1779 · report
square_loss_with_sigmoid_logits deepmind/dd_two_player_games/dd_two_player_games/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · daddd6a303235a22 · report

Tasks

Deep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections