Papers › A spin-glass model for the loss surfaces of generative adversarial networks

A spin-glass model for the loss surfaces of generative adversarial networks

7 Jan 2021arXiv:2101.02524archive 2025-07-28

Nicholas P Baskerville, Jonathan P Keating, Francesco Mezzadri, Joseph Najnudel

We present a novel mathematical model that seeks to capture the key design feature of generative adversarial networks (GANs). Our model consists of two interacting spin glasses, and we conduct an extensive theoretical analysis of the complexity of the model's critical points using techniques from Random Matrix Theory. The result is insights into the loss surfaces of large GANs that build upon prior insights for simpler networks, but also reveal new structure unique to this setting.

PaperPDFCode

Code

npbaskerville/loss-surfaces-of-gans officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections