Vasilis Syrgkanis: Oracle efficient Learning and Auction Design

Speaker: Vasilis Syrgkanis, Microsoft Research, New England

Date: Tuesday, February 28, 2017

Time: 4:00 PM to 5:00 PM Note: all times are in the Eastern Time Zone

Refreshments: 3:45 PM

Public: Yes

Location: Patil/Kiva G449

Event Type:

Room Description:

Host: Aleksander Madry

Contact: Deborah Goodwin, 617.324.7303,

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to:,,

Reminder Subject: TALK: Vasilis Syrgkanis: Oracle efficient Learning and Auction Design

> Abstract. We consider the design of online no-regret algorithms that are computationally efficient, given access to an offline optimization oracle. We present an algorithm we call Generalized Follow-the-Perturbed-Leader and provide conditions under which it achieves vanishing regret and is oracle-efficient. Our second main contribution is introducing a new adversarial auction-design framework for revenue maximization and applying our oracle-efficient learning results to the adaptive optimization of auctions. Our work extends to oracle-efficient algorithms with contextual information, learning with Maximal-in-Range approximation algorithms, and no-regret bidding in simultaneous auctions.
> Joint with: Miroslav Dudik, Nika Haghtalab, Haipeng Luo, Robert E.
> Schapire and Jennifer Wortman Vaughan

Research Areas:

Impact Areas:

See other events that are part of the Theory of Computation (TOC) 2017.

Created by Deborah Goodwin Email at Wednesday, February 22, 2017 at 9:24 AM.