Anant Raj
PhD
Max Planck Institute for lnformatics (MPI-INF)
Stochastic Convex Optimization for Over-Parametrized models

Over-parametrized models are frequently occurring phenomena in machine learning which comes with nice properties. In this work, we investigate methods to optimize such models. Our goal is to show faster convergence rate for traditional 1st order methods on such problems without extra assumptions and with similar computational cost. We also validate our theory experimentally.

Track:
Academic Track
PhD Duration:
August 1st, 2015 - November 30th, 2020
First Exchange:
October 4th, 2019 - March 31st, 2020
ELLIS Edge Newsletter
Join the 6,000+ people who get the monthly newsletter filled with the latest news, jobs, events and insights from the ELLIS Network.