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.
In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives. Our findings suggest that the convergence of current algorithms suffers due to two factors: i) presence of eigenvalues of the Jacobian of the gradient vector field with zero real-part, and ii) eigenvalues with big imaginary part. Using these findings, we design a new algorithm that overcomes some of these limitations and has better convergence properties. Experimentally, we demonstrate its superiority on training common GAN architectures and show convergence on GAN architectures that are known to be notoriously hard to train.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1705.10461")
get_code_for_paper("1705.10461")
have("1705.10461")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1705.10461.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1705.10461)
Connect an agent — have() is free.