Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization

82 Pages Posted: 25 Jun 2020 Last revised: 19 Jan 2022

See all articles by Rad Niazadeh

Rad Niazadeh

University of Chicago - Booth School of Business

Negin Golrezaei

Massachusetts Institute of Technology (MIT) - Sloan School of Management

Joshua Wang

Google Inc. - Google Research Mountain View

Fransisca Susan

Massachusetts Institute of Technology (MIT) - Sloan School of Management

Ashwinkumar Badanidiyuru

Google Inc. - Google Research Mountain View

Date Written: May 29, 2020

Abstract

Motivated by online decision-making in time-varying combinatorial environments, we study the problem of transforming offline algorithms to their online counterparts. We focus on offline combinatorial problems that are amenable to a constant factor approximation using a greedy algorithm that is robust to local errors. For such problems, we provide a general framework that efficiently transforms offline robust greedy algorithms to online ones using Blackwell approachability. We show that the resulting online algorithms have $O(\sqrt{T})$ (approximate) regret under the full information setting. We further introduce a bandit extension of Blackwell approachability that we call Bandit Blackwell approachability. We leverage this notion to transform greedy robust offline algorithms into a $O(T^{2/3})$ (approximate) regret in the bandit setting. Demonstrating the flexibility of our framework, we apply our offline-to-online transformation to several problems at the intersection of revenue management, market design, and online optimization, including product ranking optimization in online platforms, reserve price optimization in auctions, and submodular maximization. We also extend our reduction to greedy-like first-order methods used in continuous optimization, such as those used for maximizing continuous strong DR monotone submodular functions subject to convex constraints. We show that our transformation, when applied to these applications, leads to new regret bounds or improves the current known bounds. We complement our theoretical studies by conducting numerical simulations for two of our applications, in both of which we observe that the numerical performance of our transformations outperforms the theoretical guarantees in practical instances.

Keywords: Online learning, submodular optimization, revenue management, Blackwell approachability

Suggested Citation

Niazadeh, Rad and Golrezaei, Negin and Wang, Joshua and Susan, Fransisca and Badanidiyuru, Ashwinkumar, Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization (May 29, 2020). Chicago Booth Research Paper No. 20-27, Available at SSRN: https://ssrn.com/abstract=3613756 or http://dx.doi.org/10.2139/ssrn.3613756

Rad Niazadeh (Contact Author)

University of Chicago - Booth School of Business ( email )

5807 S Woodlawn Ave
Chicago, IL 60637

HOME PAGE: http://radniazadeh.github.io/

Negin Golrezaei

Massachusetts Institute of Technology (MIT) - Sloan School of Management ( email )

100 Main Street
E62-416
Cambridge, MA 02142
United States
02141 (Fax)

Joshua Wang

Google Inc. - Google Research Mountain View ( email )

1600 Amphitheatre Parkway
Second Floor
Mountain View, CA 94043
United States

Fransisca Susan

Massachusetts Institute of Technology (MIT) - Sloan School of Management ( email )

100 Main Street
E62-416
Cambridge, MA 02142
United States

Ashwinkumar Badanidiyuru

Google Inc. - Google Research Mountain View ( email )

1600 Amphitheatre Parkway
Second Floor
Mountain View, CA 94043
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
853
Abstract Views
3,242
rank
39,002
PlumX Metrics