activity
20162024
most citedBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

565 citations · 1k across the 21 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.LG2021★ 1 cited

Gradients are Not All You Need

Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz +1

Differentiable programming techniques are widely used in the community and are responsible for the machine learning renaissance of the past several decades. While these methods are…

cs.LG2021

Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping

James Martens, Andy Ballard, Guillaume Desjardins +4

Using an extended and formalized version of the Q/C map analysis of Poole et al. (2016), along with Neural Tangent Kernel theory, we identify the main pathologies present in deep n…

cs.LG2021

Learn2Hop: Learned Optimization on Rough Landscapes

Amil Merchant, Luke Metz, Sam Schoenholz +1

Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material d…

physics.comp-ph2021

dPV: An End-to-End Differentiable Solar-Cell Simulator

Sean Mann, Eric Fadel, Samuel S. Schoenholz +3

We introduce dPV, an end-to-end differentiable photovoltaic (PV) cell simulator based on the drift-diffusion model and Beer-Lambert law for optical absorption. dPV is programmed in…

cs.LG2021

Tilting the playing field: Dynamical loss functions for machine learning

Miguel Ruiz-Garcia, Ge Zhang, Samuel S. Schoenholz +1

We show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamica…