Past Events

Faculty Candidate Talk

Efficient and Ethical Data Processing -- introducing new information-theoretic tools

 

Download as iCal file

Monday, March 21, 2022, 10:30am - 12:00pm

 

Topic: Sumegha Garg Talk

Time: Mar 21, 2022 10:00 AM Eastern Time (US and Canada)

Join Zoom Meeting

https://rutgers.zoom.us/j/91762654038?pwd=SExXWEpUTlVuSXlDTjNBazd3MTFZZz09

Join by SIP

Meeting ID: 917 6265 4038

Password: 55555

One tap mobile

+13017158592,,91762654038# US (Washington DC)

+13126266799,,91762654038# US (Chicago)

Join By Phone

        +1 301 715 8592 US (Washington DC)

        +1 312 626 6799 US (Chicago)

        +1 646 558 8656 US (New York)

        +1 253 215 8782 US (Tacoma)

        +1 346 248 7799 US (Houston)

        +1 669 900 9128 US (San Jose)

Meeting ID: 917 6265 4038

Find your local number: https://rutgers.zoom.us/u/at29Na2a3

Join by Skype for Business

https://rutgers.zoom.us/skype/91762654038

If you have any questions, please <a href="https://it.rutgers.edu/help-support/">contact the Office of Information Technology Help Desk</a>

Speaker:  Sumegha Garg

Bio

 Sumegha Garg is a Michael O. Rabin postdoctoral fellow in theoretical computer science at Harvard University. She received her Ph.D. in Computer Science from Princeton University in 2020, advised by Mark Braverman. She uses her background in computational complexity theory to answer fundamental questions in applied areas such as learning, data streaming, and cryptography. In particular, she is interested in determining the limits of space-efficient computing and establishing the foundations of responsible computing. Her awards include Siebel Scholarship (2019-20), Microsoft Dissertation Grant (2019) and Rising Star in EECS (2019).

Location : Via Zoom

Event Type: Faculty Candidate Talk

Abstract: Data-driven algorithms have seen great success in a wide range of domains, from product recommendations to cyber-security and healthcare. The ever-expanding use of these algorithms brings in new efficiency and ethical concerns. Firstly, when analyzing massive amounts of data, memory is increasingly becoming a bottleneck computational resource. Secondly, as data-driven decision-making systems are being used to make important decisions about humans, they raise a host of fairness concerns and fears for potential discrimination.In this talk, I'll give an overview of my efforts to understand these concerns using modern mathematical tools from computational complexity theory and information theory. I'll then dig deeper into two results that illustrate the efficacy of information-theoretic techniques in quantifying memory usage as well as characterizing challenges in algorithmic fairness. First, I'll introduce the coin problem – given independent coin tosses, detect which way a coin is biased – and show that this problem is at the heart of hardness results for many data streaming problems. I’ll go on to describe new techniques we developed to determine the memory needed for solving the coin problem. Second, I'll show how informativeness of predictions on a subpopulation plays a key role in connecting various conflicting approaches to algorithmic fairness.

Organization

Rutgers University School of Arts and Sciences

Contact  Aaron Bernstein