Gauthier Gidel

A Minimax Theorem for Nonconcave-Nonconvex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets

2020 · arXiv (Cornell University)

Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-based generative modeling and self-play techniques in reinforcement learning which have been applied …

In-Context Learning Can Re-learn Forbidden Tasks

2024 · arXiv (Cornell University)

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safety training is that it algorithmically forbids the model from answering …