Jacob Abernethy

jabernet's picture
University: 
University of Michigan - Ann Arbor
Unit: 
Engineering
Department: 
Electrical Engineering and Computer Science
Title: 
Assistant Professor
Short bio: 

Degree: PhD, Computer Science, UC Berkeley, 2011

Research summary: 

Research Interests: Jake's research draws from the field of Machine Learning (ML), but he has devoted much attention to a range of areas, including game theory, decision theory, optimization, market mechanism design, and financial applications. He is particularly interested in how algorithms utilized in ML, such as those for discovering patterns in data, are strongly related to methods used in large-scale optimization, as well as strategies for hedging financial derivatives and setting prices in securities markets.

Research Areas: Artificial Intelligence; Theory of Computation.

Areas of Specialty: Machine Learning; Electronic Commerce; Design and Analysis of Algorithms.

Recent publications: 

Qingsi Wang, Shang-Pin Sheng, J.A., Mingyan Liu; Jamming Defense Against a Resource-Replenishing Adversary in Multi-channel Wireless Systems, 2014, (WiOpt) International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks.

J.A., Sindhu Kutty, S{\'e}bastien Lahaie, Rahul Sami; Information aggregation in exponential family markets, 2014, (EC) Proceedings of the 15th ACM conference on Economics and computation.

J.A., Rafael M Frongillo, Xiaolong Li, Jennifer Wortman Vaughan; A general volume-parameterized market making framework, 2014, (EC) Proceedings of the 15th ACM conference on Economics and computation.

J.A., Chansoo Lee, Abhinav Sinha, Ambuj Tewari; Online Linear Optimization via Smoothing, 2014, (COLT) Conference on Learning Theory.

J.A., Peter Bartlett, Rafael Frongillo, Andre Wibisono; How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal, 2013, (NIPS) Advances in Neural Information Processing Systems.

J.A., Satyen Kale; Adaptive Market Making via Online Learning, 2013, (NIPS) Advances in Neural Information Processing Systems.

Brendan McMahan, J.A.; Minimax optimal algorithms for unconstrained linear optimization, 2013, (NIPS) Advances in Neural Information Processing Systems.

J.A., Kareem Amin, Moez Draief, Michael Kearns; Large-Scale Bandit Problems and $\{$KWIK$\}$ Learning, 2013, (ICML) Proceedings of the 30th International Conference on Machine Learning.