A Stochastic Quasi-Newton Method for Online Convex Optimization
Year: 2007
Type: article
Abstract: We develop stochastic variants of the wellknown BFGS quasi-Newton optimization method, in both full and memory-limited (LBFGS) forms, for online optimization of convex functions. The resulting algorithm performs comparably to a well-tuned natural gradient descent but is scalable to very high-dimensional problems. On standard benchmarks in natural language processing, it asymptotically outperforms previous stochastic gradient methods for parameter estimation in conditional random fields. We are working on analyzing the convergence of online (L)BFGS, and extending it to nonconvex optimization problems. 1
Authors: Nicol N. Schraudolph, Jin Yu, Simon Günter
Institutions: Data61, Australian National University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1491622225