1.1k citations · 3.5k across the 39 of their papers we have counts for
16 papers · 1 filter
High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise
Liam Madden, Emiliano Dall'Anese, Stephen Becker
Stochastic gradient descent is one of the most common iterative algorithms used in machine learning and its convergence analysis is a rich area of research. Understanding its conve…
Optimization and Learning with Information Streams: Time-varying Algorithms and Applications
Emiliano Dall'Anese, Andrea Simonetto, Stephen Becker +1
There is a growing cross-disciplinary effort in the broad domain of optimization and learning with streams of data, applied to settings where traditional batch optimization techniq…
The Chen-Teboulle algorithm is the proximal point algorithm
Stephen Becker
We revisit the Chen-Teboulle algorithm using recent insights and show that this allows a better bound on the step-size parameter.
Safe Feature Elimination for Non-Negativity Constrained Convex Optimization
James Folberth, Stephen Becker
Inspired by recent work on safe feature elimination for -norm regularized least-squares, we develop strategies to eliminate features from convex optimization problems with non-n…
Stochastic Subspace Descent
David Kozak, Stephen Becker, Alireza Doostan +1
We present two stochastic descent algorithms that apply to unconstrained optimization and are particularly efficient when the objective function is slow to evaluate and gradients a…
Tensor Robust Principal Component Analysis: Better recovery with atomic norm regularization
Derek Driggs, Stephen Becker, Jordan Boyd-Graber
This paper studies tensor-based Robust Principal Component Analysis (RPCA) using atomic-norm regularization. Given the superposition of a sparse and a low-rank tensor, we present c…