Liu Ziyin, Joshua Albrecht, Abraham Fetterman, Maksis Knutins, James Simon, Daniel Geisz
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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. Despite SSL's simplicity, however, the field lacks a complete theoretical understanding of the paradigm. A promising place to start may be the fact that although there exist
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15438")
get_code_for_paper("2303.15438")
have("2303.15438")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.15438.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.15438)
Connect an agent — have() is free.