activity
20152023
most citedMathematics of Deep Learning

80 citations · 138 across the 20 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.LG20195 cited

Basis Pursuit and Orthogonal Matching Pursuit for Subspace-preserving Recovery: Theoretical Analysis

Daniel P. Robinson, Rene Vidal, Chong You

Given an overcomplete dictionary and a signal for some sparse vector whose nonzero entries correspond to linearly independent columns of , classical sparse…

cs.LG2019

The fastest prox in the west

Benjamín Béjar, Ivan Dokmanić, René Vidal

Proximal operators are of particular interest in optimization problems dealing with non-smooth objectives because in many practical cases they lead to optimization algorithms whose…

cs.LG2019

On the Regularization Properties of Structured Dropout

Ambar Pal, Connor Lane, René Vidal +1

Dropout and its extensions (eg. DropBlock and DropConnect) are popular heuristics for training neural networks, which have been shown to improve generalization performance in pract…

eess.SP2019

What is the Largest Sparsity Pattern that Can Be Recovered by 1-Norm Minimization?

Mustafa D. Kaba, Mengnan Zhao, Rene Vidal +2

Much of the existing literature in sparse recovery is concerned with the following question: given a sparsity pattern and a corresponding regularizer, derive conditions on the dict…

cs.CV2019

Representation Learning on Visual-Symbolic Graphs for Video Understanding

Effrosyni Mavroudi, Benjamín Béjar Haro, René Vidal

Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture th…

math.OC2019

Conformal Symplectic and Relativistic Optimization

Guilherme França, Jeremias Sulam, Daniel P. Robinson +1

Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both correspondi…