Papers › On the Stepwise Nature of Self-Supervised Learning

On the Stepwise Nature of Self-Supervised Learning

27 Mar 2023arXiv:2303.15438archive 2025-07-28

James B. Simon, Maksis Knutins, Liu Ziyin, Daniel Geisz, Abraham J. Fetterman, Joshua Albrecht

We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated steps. We arrive at this conclusion via the study of a linearized model of Barlow Twins applicable to the case in which the trained network is infinitely wide. We solve the training dynamics of this model from small initialization, finding that the model learns the top eigenmodes of a certain contrastive kernel in a stepwise fashion, and obtain a closed-form expression for the final learned representations. Remarkably, we then see the same stepwise learning phenomenon when training deep ResNets using the Barlow Twins, SimCLR, and VICReg losses. Our theory suggests that, just as kernel regression can be thought of as a model of supervised learning, kernel PCA may serve as a useful model of self-supervised learning.

PaperPDFCode

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

Code

gitlab.com/generally-intelligent/ssl_dynamics officialmentioned in papermentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Self-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBarlow TwinsBatch NormalizationBottleneck Residual BlockColorJitterConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingKaiming InitializationMax PoolingNT-XentPCARandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLR

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