Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability
Pierre Marion
Gradient descent in deep learning may operate at the edge of stability (EoS), a regime in which the largest eigenvalue of the loss Hessian hovers near the stability threshold …
cs.LG2026
Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
Sacchit Kale, Piyushi Manupriya, Pierre Marion +2
Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work sugges…
cs.LG2024
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Pierre Marion, Anna Korba, Peter Bartlett +6
We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling pr…