Skip to main content.
Advanced search >
<< Back to previous page Print

<< Wednesday, September 06, 2017 >>

Remind me

Tell a friend

Add to my Google calendar (bCal)

Download to my calendar

Bookmark and ShareShare

Stochastic First-Order Methods in Data Analysis and Reinforcement Learning

Seminar: Neyman Seminar | September 6 | 4-5 p.m. | 1011 Evans Hall

Mengdi Wang, Princeton University

Department of Statistics

Stochastic first-order methods provide a basic algorithmic tool for online learning and data analysis. In this talk, we survey several innovative applications including risk-averse optimization, online principal component analysis, dynamic network partition, Markov decision problems and reinforcement learning. We will show that convergence analysis of the stochastic optimization algorithms provide near-optimal sample complexity, run-time complexity and regret analysis in a variety of offline and online learning applications.

(510) 642-2781