Name
Abstract | ||
|---|---|---|
In this work, we propose a (linearized) Alternating Direction Method-of-Multipliers (ADMM) algorithm for minimizing a convex function subject to a nonconvex constraint. We focus on the special case where such constraint arises from the specification that a variable should lie in the range of a neural network. This is motivated by recent successful applications of Generative Adversarial Networks (GANs) in tasks like compressive sensing, denoising and robustness against adversarial examples. The derived rates for our algorithm are characterized in terms of certain geometric properties of the generator network, which we show hold for feedforward architectures, under mild assumptions. Unlike gradient descent (GD), it can efficiently handle non-smooth objectives as well as exploit efficient partial minimization procedures, thus being faster in many practical scenarios. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | neural networks,generative adversarial network (gan) |
Field | DocType | Volume |
Computer science,Artificial intelligence,Generative grammar,Prior probability,Machine learning | Conference | 32 |
ISSN | Citations | PageRank |
1049-5258 | 1 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fabian Latorre Gomez | 1 | 1 | 0.34 |
| Armin Eftekhari | 2 | 129 | 12.42 |
| Volkan Cevher | 3 | 6 | 1.77 |