arXiv subjects

Ashia C. Wilson

Publications and source records attributed to Ashia C. Wilson.

24 records · Page 2Linked to original sources

arXiv2018

On Symplectic Optimization

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 lower bounds. But their heuristic construction has hindered their full integration into the practical machine-learning algorithmic toolbox, and has limited their scope. In this paper we build on recent work which casts acceleration as a phenomenon best explained in continuous time, and we augment that picture by providing a systematic methodology for converting continuous-time dynamics into discrete-time algorithms while retaining oracle rates. Our framework is based on ideas from Hamiltonian dynamical systems and symplectic integration. These ideas have had major impact in many areas in applied mathematics, but have not yet been seen to have a relationship with optimization.

stat.CO↗

arXiv2017

Breaking Locality Accelerates Block Gauss-Seidel

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 coordinates is chosen ahead of time. We show that this setting is too restrictive, constructing instances where breaking locality by running non-accelerated Gauss-Seidel with randomly sampled coordinates substantially outperforms accelerated Gauss-Seidel with any fixed partitioning. Motivated by this finding, we analyze the accelerated block Gauss-Seidel algorithm in the random coordinate sampling setting. Our analysis captures the benefit of acceleration with a new data-dependent parameter which is well behaved when the matrix sub-blocks are well-conditioned. Empirically, we show that accelerated Gauss-Seidel with random coordinate sampling provides speedups for large scale machine learning tasks when compared to non-accelerated Gauss-Seidel and the classical conjugate-gradient algorithm.

math.OC↗

arXiv2016

Posteriors, conjugacy, and exponential families for completely random measures

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 priors as a sequence of finite draws using a size-biasing approach---and how to represent full Bayesian nonparametric models via finite marginals. Motivated by conjugate priors based on exponential family representations of likelihoods, we introduce a notion of exponential families for CRMs, which we call exponential CRMs. This construction allows us to specify automatic Bayesian nonparametric conjugate priors for exponential CRM likelihoods. We demonstrate that our exponential CRMs allow particularly straightforward recipes for size-biased and marginal representations of Bayesian nonparametric models. Along the way, we prove that the gamma process is a conjugate prior for the Poisson likelihood process and the beta prime process is a conjugate prior for a process we call the odds Bernoulli process. We deliver a size-biased representation of the gamma process and a marginal representation of the gamma process coupled with a Poisson likelihood process.

math.ST↗

arXiv2016

A Variational Perspective on Accelerated Methods in Optimization

Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelerated methods from a continuous-time perspective. We show that there is a Lagrangian functional that we call the \emph{Bregman Lagrangian} which generates a large class of accelerated methods in continuous time, including (but not limited to) accelerated gradient descent, its non-Euclidean extension, and accelerated higher-order gradient methods. We show that the continuous-time limit of all of these methods correspond to traveling the same curve in spacetime at different speeds. From this perspective, Nesterov's technique and many of its generalizations can be viewed as a systematic way to go from the continuous-time curves generated by the Bregman Lagrangian to a family of discrete-time accelerated algorithms.

math.OC↗

arXiv2015

On Accelerated Methods in Optimization

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 Nesterov's accelerated gradient descent, accelerated mirror descent, and accelerated cubic-regularized Newton's method, among others. In this paper, we show that the family of higher-order gradient methods in discrete time (generalizing gradient descent) corresponds to a family of first-order rescaled gradient flows in continuous time. On the other hand, the family of {\em accelerated} higher-order gradient methods (generalizing accelerated mirror descent) corresponds to a family of second-order differential equations in continuous time, each of which is the Euler-Lagrange equation of a family of Lagrangian functionals. We also study the exponential variant of the Nesterov Lagrangian, which corresponds to a generalization of Nesterov's restart scheme and achieves a linear rate of convergence in discrete time. Finally, we show that the family of Lagrangians is closed under time dilation (an orbit under the action of speeding up time), which demonstrates the universality of this Lagrangian view of acceleration in optimization.

math.OC↗

arXiv2013

Streaming Variational Bayes

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 posterior according to a user-specified approximation batch primitive. We demonstrate the usefulness of our framework, with variational Bayes (VB) as the primitive, by fitting the latent Dirichlet allocation model to two large-scale document collections. We demonstrate the advantages of our algorithm over stochastic variational inference (SVI) by comparing the two after a single pass through a known amount of data---a case where SVI may be applied---and in the streaming setting, where SVI does not apply.

stat.ML↗