Back to Events

Seminar Series

February 16

EECS Special Seminar: Kevin Jamieson, "Efficient scalable algorithms for adaptive data collection"

Kevin Jamieson
UC Berkeley

Part Of

4:00P
- 5:00P

Location

32-G449
Add to Calendar 2017-02-16 16:00:00 2017-02-16 17:00:00 America/New_York EECS Special Seminar: Kevin Jamieson, "Efficient scalable algorithms for adaptive data collection" Abstract: In many applications, data-driven discovery is limited by the rate of data collection: the skilled labor it takes to operate a pipette, the time to execute a long-running physics simulation, the patience of an infant to remain still in an MRI, or the cost of labeling large corpuses of complex images. A powerful paradigm to extract the most information with such limited resources is active learning, or adaptive data collection, which leverages already-collected data to guide future measurements in a closed loop. But being convinced that data-collection should be adaptive is not the same thing as knowing how to adapt in a way that is both sample efficient and reliable. In this talk, I will present several examples of my provably reliable -- and practical -- adaptive data collection algorithms being applied in the real-world. In particular, I will show how my adaptive algorithms are used each week to crowd-source the winner of the New Yorker Magazine Cartoon Caption Contest. I will also discuss my application of adaptive learning concepts at Google to accelerate the tuning of deep networks in a highly parallelized environment of thousands of GPUs.Bio: Kevin Jamieson is a postdoctoral researcher working with Professor Benjamin Recht in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. He is interested in the theory and practice of machine learning algorithms that sequentially collect data using an adaptive strategy. This includes active learning, multi-armed bandit problems, and stochastic optimization. Kevin received his Ph.D. from the University of Wisconsin - Madison under the advisement of Robert Nowak. Prior to his doctoral work, Kevin received his B.S. from the University of Washington, and an M.S. from Columbia University, both in electrical engineering. 32-G449

EECS/IDSS Special Seminar: Jamie Morgenstern "Towards a Theory of Fairness in Machine Learning"

Jamie Morgenstern
University of Pennsylania

Part Of

3:00P
- 4:00P

Location

34-401 (grier A)
Add to Calendar 2017-02-16 15:00:00 2017-02-16 16:00:00 America/New_York EECS/IDSS Special Seminar: Jamie Morgenstern "Towards a Theory of Fairness in Machine Learning" Abstract: Algorithm design has moved from being a tool used exclusively for designing systems to one used to present people with personalized content, advertisements, and other economic opportunities. Massive amounts of information is recorded about people's online behavior including the websites they visit, the advertisements they click on, their search history, and their IP address. Algorithms then use this information for many purposes: to choose which prices to quote individuals for airline tickets, which advertisements to show them, and even which news stories to promote. These systems create new challenges for algorithm design. When a person's behavior influences the prices they may face in the future, they may have a strong incentive to modify their behavior to improve their long-term utility; therefore, these algorithms' performance should be resilient to strategic manipulation. Furthermore, when an algorithm makes choices that affect people's everyday lives, the effects of these choices raise ethical concerns such as whether the algorithm's behavior violates individuals' privacy or whether the algorithm treats people fairly.Machine learning algorithms in particular have received much attention for exhibiting bias, or unfairness, in a large number ofcontexts. In this talk, I will describe my recent work on developing a definition of fairness for machine learning. One definition offairness, encoding the notion of 'fair equality of opportunity', informally, states that if one person has higher expected quality than another person, the higher quality person should be given at least as much opportunity as the lower quality person. I will present aresult characterizing the performance degradation of algorithms which satisfy this condition in the contextual bandits setting. To complement these theoretical results, I then present the results of several empirical evaluations of fair algorithms. I will also briefly describe my work on designing algorithms whose performance guarantees are resilient to strategic manipulation oftheir inputs, and machine learning for optimal auction design.Speaker bio: Jamie Morgenstern is a Warren Center postdoctoral fellow in Computer Science and Economics at the University of Pennsylvania. She received her Ph.D. in Computer Science from Carnegie Mellon University in 2015, and her B.S. in Computer Science and B.A. in Mathematics from the University of Chicago in 2010. Her research focuses on machine learning for mechanism design, fairness in machine learning, and algorithmic game theory. She received a Microsoft Women's Research Scholarship, anNSF Graduate Research Fellowship, and a Simons Award for Graduate Students in Theoretical Computer Science. 34-401 (grier A)