31 citations · 123 across the 9 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
The staircase property: How hierarchical structure can guide deep learning
Emmanuel Abbe, Enric Boix-Adsera, Matthew Brennan +2
This paper identifies a structural property of data distributions that enables deep neural networks to learn hierarchically. We define the "staircase" property for functions over t…
math.PR2021★ 7 cited
De Finetti-Style Results for Wishart Matrices: Combinatorial Structure and Phase Transitions
Matthew Brennan, Guy Bresler, Brice Huang
A recent line of work has studied the relationship between the Wishart matrix , where has i.i.d. standard Gaussian entries, and the correspo…