3.6k citations · 10.6k across the 54 of their papers we have counts for
Showing 2021 · cs.LGShow all
2 papers · 2 filters
cs.LG2021★ 5 cited
No One Representation to Rule Them All: Overlapping Features of Training Methods
Raphael Gontijo-Lopes, Yann Dauphin, Ekin D. Cubuk
Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-perf…
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…