546 citations · 1.3k across the 14 of their papers we have counts for
15 papers
Accelerated Stochastic Optimization Methods under Quasar-convexity
Qiang Fu, Dongchu Xu, Ashia Wilson
Non-convex optimization plays a key role in a growing number of machine learning applications. This motivates the identification of specialized structure that enables sharper theor…
Sufficient conditions for non-asymptotic convergence of Riemannian optimisation methods
Vishwak Srinivasan, Ashia Wilson
Motivated by energy based analyses for descent methods in the Euclidean setting, we investigate a generalisation of such analyses for descent methods over Riemannian manifolds. In…
Algorithms that Approximate Data Removal: New Results and Limitations
Vinith M. Suriyakumar, Ashia C. Wilson
We study the problem of deleting user data from machine learning models trained using empirical risk minimization. Our focus is on learning algorithms which return the empirical ri…
Multilevel Optimization for Inverse Problems
Simon Weissmann, Ashia Wilson, Jakob Zech
Inverse problems occur in a variety of parameter identification tasks in engineering. Such problems are challenging in practice, as they require repeated evaluation of computationa…
Approximate Cross-validation: Guarantees for Model Assessment and Selection
Ashia Wilson, Maximilian Kasy, Lester Mackey
Cross-validation (CV) is a popular approach for assessing and selecting predictive models. However, when the number of folds is large, CV suffers from a need to repeatedly refit a…
The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally
Lydia T. Liu, Ashia Wilson, Nika Haghtalab +3
The long-term impact of algorithmic decision making is shaped by the dynamics between the deployed decision rule and individuals' response. Focusing on settings where each individu…
Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions
Ashia Wilson, Lester Mackey, Andre Wibisono
We present a family of algorithms, called descent algorithms, for optimizing convex and non-convex functions. We also introduce a new first-order algorithm, called rescaled gradien…
On Symplectic Optimization
Michael Betancourt, Michael I. Jordan, Ashia C. Wilson
Accelerated gradient methods have had significant impact in machine learning -- in particular the theoretical side of machine learning -- due to their ability to achieve oracle low…
The Marginal Value of Adaptive Gradient Methods in Machine Learning
Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern +2
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural n…
Breaking Locality Accelerates Block Gauss-Seidel
Stephen Tu, Shivaram Venkataraman, Ashia C. Wilson +3
Recent work by Nesterov and Stich showed that momentum can be used to accelerate the rate of convergence for block Gauss-Seidel in the setting where a fixed partitioning of the coo…
A Lyapunov Analysis of Momentum Methods in Optimization
Ashia C. Wilson, Benjamin Recht, Michael I. Jordan
Momentum methods play a significant role in optimization. Examples include Nesterov's accelerated gradient method and the conditional gradient algorithm. Several momentum methods a…
A Variational Perspective on Accelerated Methods in Optimization
Andre Wibisono, Ashia C. Wilson, Michael I. Jordan
Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceler…
On Accelerated Methods in Optimization
Andre Wibisono, Ashia C. Wilson
In convex optimization, there is an {\em acceleration} phenomenon in which we can boost the convergence rate of certain gradient-based algorithms. We can observe this phenomenon in…
Posteriors, conjugacy, and exponential families for completely random measures
Tamara Broderick, Ashia C. Wilson, Michael I. Jordan
We demonstrate how to calculate posteriors for general CRM-based priors and likelihoods for Bayesian nonparametric models. We further show how to represent Bayesian nonparametric p…
Streaming Variational Bayes
Tamara Broderick, Nicholas Boyd, Andre Wibisono +2
We present SDA-Bayes, a framework for (S)treaming, (D)istributed, (A)synchronous computation of a Bayesian posterior. The framework makes streaming updates to the estimated posteri…