51 citations · 97 across the 8 of their papers we have counts for
4 papers · 1 filter
On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret +4
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii)…
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…
Dual Gauss-Newton Directions for Deep Learning
Vincent Roulet, Mathieu Blondel
Inspired by Gauss-Newton-like methods, we study the benefit of leveraging the structure of deep learning objectives, namely, the composition of a convex loss function and of a nonl…
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Michael E. Sander, Joan Puigcerver, Josip Djolonga +2
The top-k operator returns a sparse vector, where the non-zero values correspond to the k largest values of the input. Unfortunately, because it is a discontinuous function, it is…