We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| facebookresearch/GAN-optimization-landscape | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| define_model_loss | Ran | facebookresearch/GAN-optimization-landscape/train_mnist.py code served (permissive licence) · get_code("d65e62e1114565ac") |
| normalize_module2D | Ran | facebookresearch/GAN-optimization-landscape/train_mnist.py code served (permissive licence) · get_code("ccf8af9953863e6b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Generative adversarial networks have been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks. In this paper, we propose new visualization techniques for the optimization landscapes of GANs that enable us to study the game vector field resulting from the concatenation of the gradient of both players. Using these visualization techniques we try to bridge the gap between theory and practice by showing empirically that the training of GANs exhibits significant rotations around Local Stable Stationary Points (LSSP), similar to the one predicted by theory on toy examples. Moreover, we provide empirical evidence that GAN training converge to a stable stationary point which is a saddle point for the generator loss, not a minimum, while still achieving excellent performance.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1906.04848")
get_code_for_paper("1906.04848")
have("1906.04848")
Connect an agent — have() is free.