Tolga Ergen, Mert Pilanci, Arda Sahiner, Batu Ozturkler, John Pauly, Morteza Mardani, Burak Bartan
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.
Generative Adversarial Networks (GANs) are commonly used for modeling complex distributions of data. Both the generators and discriminators of GANs are often modeled by neural networks, posing a non-transparent optimization problem which is non-convex and non-concave over the generator and discriminator, respectively. Such networks are often heuristically optimized with gradient descent-ascent (GDA), but it is unclear whether the optimization problem contains any saddle points, or whether heuristic methods can find them in practice. In this work, we analyze the training of Wasserstein GANs with two-layer neural network discriminators through the lens of convex duality, and for a variety of generators expose the conditions under which Wasserstein GANs can be solved exactly with convex optimization approaches, or can be represented as convex-concave games. Using this convex duality interpretation, we further demonstrate the impact of different activation functions of the discriminator. Our observations are verified with numerical results demonstrating the power of the convex interpretation, with applications in progressive training of convex architectures corresponding to linear generators and quadratic-activation discriminators for CelebA image generation. The code for our experiments is available at https://github.com/ardasahiner/ProCoGAN.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.05680")
get_code_for_paper("2107.05680")
have("2107.05680")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2107.05680.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2107.05680)
Connect an agent — have() is free.