A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)

no code implementations • 25 Oct 2017 • Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford

This work provides a simplified proof of the statistical minimax optimality of (iterate averaged) stochastic gradient descent (SGD), for the special case of least squares.

Data Driven Resource Allocation for Distributed Learning

no code implementations • 15 Dec 2015 • Travis Dick, Mu Li, Venkata Krishna Pillutla, Colin White, Maria Florina Balcan, Alex Smola

In distributed machine learning, data is dispatched to multiple machines for processing.