A Stochastic Newton Algorithm for Distributed Convex Optimization
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore a 35-minute lecture on a novel stochastic Newton algorithm for distributed convex optimization presented by Brian Bullins from Purdue University at the Simons Institute. Delve into the proposed method for homogeneous distributed stochastic convex optimization, where machines calculate stochastic gradients and Hessian-vector products of the same population objective. Learn how this algorithm reduces communication rounds without compromising performance, particularly for quasi-self-concordant objectives like logistic regression. Examine the convergence guarantees and empirical evidence supporting the effectiveness of this approach in optimization and algorithm design.
Syllabus
A Stochastic Newton Algorithm for Distributed Convex Optimization
Taught by
Simons Institute
Related Courses
Cloud Computing Concepts, Part 1University of Illinois at Urbana-Champaign via Coursera Cloud Computing Concepts: Part 2
University of Illinois at Urbana-Champaign via Coursera Reliable Distributed Algorithms - Part 1
KTH Royal Institute of Technology via edX Introduction to Apache Spark and AWS
University of London International Programmes via Coursera Réalisez des calculs distribués sur des données massives
CentraleSupélec via OpenClassrooms