1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.LG2024★ 1 cited
Stepping on the Edge: Curvature Aware Learning Rate Tuners
Vincent Roulet, Atish Agarwala, Jean-Bastien Grill +3
Curvature information -- particularly, the largest eigenvalue of the loss Hessian, known as the sharpness -- often forms the basis for learning rate tuners. However, recent work ha…
stat.ML2024
Learning with Fitzpatrick Losses
Seta Rakotomandimby, Jean-Philippe Chancelier, Michel de Lara +1
Fenchel-Young losses are a family of convex loss functions, encompassing the squared, logistic and sparsemax losses, among others. Each Fenchel-Young loss is implicitly associated…