Seth Viren Neel   

Screen Shot 2018-11-28 at 9.48.56 PMHi! I’m a fourth year Ph.D. candidate in Statistics at The Wharton School, University of Pennsylvania. I’m lucky to be advised by Michael Kearns and Aaron Roth and supported by a NSF Graduate Fellowship . My primary research (Google Scholar) interests are in theoretical computer science and machine learning. Specifically in incorporating ethical notions of fairness and privacy into tools for data analysis and artificial intelligence. This works fits into the growing fields of algorithmic fairness and differential privacy. I graduated with a math degree from Harvard in 2015, and am a co-founder of  Welligence, a fintech company focused on the energy sector.

Research – Differential Privacy Fairness in Machine Learning

All author ordering is strictly alphabetical. My research has two threads:

  1. Fairness in Machine Learning (design of new algorithms and fairness notions, in the online, bandit, batch settings)
  2. The study of fundamental problems in differential privacy, with an emphasis on private learning and adaptive data analysis

In progress: Approximately Optimal Private Truthful Allocations, Fairness by Committee, Smoothed Analysis of Private Learning, Efficient Private Synthetic Data Generation

 An Empirical Study of Rich Subgroup Fairness for Machine Learning [FAT* 2019]

Code on my Github and developed further by the AlgoWatch Team 

Fair Algorithms for Learning in Allocation Problems [FAT* 2019]

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness [ICML 2018]

Aztec Castles and the dP3 Quiver [Journal of Physics A 2015]

Mahalanobis Matching and Equal Percent Bias Reduction[Senior Thesis, Harvard ’15]

Plane Partitions and Domino Tilings [Intel Science Talent Search Semifinalist, 2011]

Talks

Upcoming:

  • Stanford Computer Science Dept. Seminar, 3.4.19.

Recent:

Media

Forbes 30 under 30 in Energy 2019

The Future of Entrepreneurship is Students 
(Forbes, May 2018)
Screen Shot 2018-06-08 at 1.21.35 AM.png

Facebook's Racially Targeted Ads Aren't as Racist As You Think

(Wired, Nov. 2016)

The Best Time to Play Powerball Could Have Been 600m Ago

(CNBC, Jan. 2016)

Contact

Office(s):  416B‐1 B-Wing, 3401 Walnut Street, Philadelphia, PA (CompSci), 1635 Market St. 16th Floor, Philadelphia, PA (Welligence)

Email(s): firstname.lastname@welligence.com (company) fullname@wharton.upenn.edu (academic)

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s