4 papers
Trust The Typical
Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust…
Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphs
Oluwatosin Akande, Patrick Dondl, Kanan Gupta +2
We study the momentum-based minimization of a diffuse perimeter functional on Euclidean spaces and on graphs with applications to semi-supervised classification tasks in machine le…
Nesterov acceleration in benignly non-convex landscapes
Kanan Gupta, Stephan Wojtowytsch
While momentum-based optimization algorithms are commonly used in the notoriously non-convex optimization problems of deep learning, their analysis has historically been restricted…
Nesterov acceleration despite very noisy gradients
Kanan Gupta, Jonathan W. Siegel, Stephan Wojtowytsch
We present a generalization of Nesterov's accelerated gradient descent algorithm. Our algorithm (AGNES) provably achieves acceleration for smooth convex and strongly convex minimiz…