Ellen Vitercik

About me:

I am a fifth-year PhD student in the Computer Science Department at Carnegie Mellon University (CMU), where I am advised by Nina Balcan and Tuomas Sandholm. I am broadly interested in machine learning theory, artificial intelligence, algorithm design, and the interface between economics and computation. I am a recipient of the IBM PhD Fellowship, the Fellowship in Digital Health from CMU's Center for Machine Learning and Health, and the NSF Graduate Research Fellowship.

In 2015, I received a Bachelor of Arts degree from Columbia, where I majored in math. In 2018, I interned at Microsoft Research New England, where I worked with Christian Borgs, Jennifer Chayes, and Adam Kalai. In 2019, I interned at Google Research New York, where I worked with Andrés Muñoz Medina, Umar Syed, and Sergei Vassilvitskii.

CV /
Email /

How Much Data is Sufficient to Learn High-Performing Algorithms?

with Maria-Florina Balcan, Dan DeBlasio, Travis Dick, Carl Kingsford, and Tuomas Sandholm

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees

with Maria-Florina Balcan and Tuomas Sandholm
AAAI 2020

Estimating Approximate Incentive Compatibility

with Maria-Florina Balcan and Tuomas Sandholm
EC 2019
Exemplary AI Track Paper Award (EC 2019)
Best Presentation by a Student or Postdoctoral Researcher (EC 2019)
Preliminary version in the EC Workshop on Machine Learning in the Presence of Strategic Behavior 2019

Learning to Prune: Speeding up Repeated Computations

with Daniel Alabi, Adam Tauman Kalai, Katrina Ligett, Cameron Musco, and Christos Tzamos
COLT 2019

Algorithmic Greenlining: An Approach to Increase Diversity

with Christian Borgs, Jennifer Chayes, Nika Haghtalab, and Adam Tauman Kalai
AIES 2019

Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization

with Maria-Florina Balcan and Travis Dick
FOCS 2018
Preliminary versions in the ICML Workshop on Private Secure Machine Learning 2017 and the ICML Workshop on Privacy in Machine Learning and Artificial Intelligence 2018

Learning to Branch

with Maria-Florina Balcan, Travis Dick, and Tuomas Sandholm
ICML 2018

A General Theory of Sample Complexity for Multi-Item Profit Maximization

with Maria-Florina Balcan and Tuomas Sandholm
EC 2018
Preliminary versions in the EC Workshop on Algorithmic Game Theory and Data Science 2017, the AAMAS-IJCAI Workshop on Agents and Incentives in Artificial Intelligence 2018, and the EC ACM/INFORMS Workshop on Market Design 2019

Synchronization Strings: Channel Simulations and Interactive Coding for Insertions and Deletions

with Bernhard Haeupler and Amirbehshad Shahrasbi
ICALP 2018

Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems

with Maria-Florina Balcan, Vaishnavh Nagarajan, and Colin White
COLT 2017

Sample Complexity of Automated Mechanism Design

with Maria-Florina Balcan and Tuomas Sandholm
NIPS 2016

Learning Combinatorial Functions from Pairwise Comparisons

with Maria-Florina Balcan and Colin White
COLT 2016

New Frontiers of Automated Mechanism Design for Pricing and Auctions

ICML 2018, AAAI 2019, EC 2019, STOC 2019, AAAI 2020 tutorial

Differentially Private Algorithm and Auction Configuration

CMU Theory Lunch 2017
Subset of material from Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization

CMU 10-701: Introduction to Machine Learning

TA for Ziv Bar-Joseph and Barnabás Póczos
Fall 2017
Won the Machine Learning Department's Teaching Assistant of the Year award.

Columbia COMS W3261: Computer Science Theory

TA for Tal Malkin
Spring 2015

The photo of rust at the top of the page is by Carol Murray. See the full photo here and all of her photos here.