Computer Science Seminar: Kavya Ravichandran (Toyota Technological Institute at Chicago)

December 15, 2025 | 11:00am - 12:00pm

Milstein 912 & Zoom

Add to Calendar 2025-12-15 11:00:00 2025-12-15 12:00:00 Computer Science Seminar: Kavya Ravichandran (Toyota Technological Institute at Chicago) Speaker: Kavya Ravichandran (Toyota Technological Institute at Chicago) Title: Sequential and Social Decision-Making: Improving Multi-Armed Bandits and Pessimism Traps The seminar will be available for in-person and Zoom participation. To participate online, please email inquiry-cs@barnard.edu to receive the Zoom link. We are often faced with decisions that require us to invest effort before reaping reward — for instance, persevering through higher education or starting a business. In this talk, I will share my recent work on theoretical models for making such decisions based on (1) one’s interaction with the environment and (2) decisions of others in one’s community. First, I will discuss the improving multi-armed bandits problem, in which an agent is deciding between k different options, each of which has more reward the more they interact with it. The agent's goal is to maximize their total reward. We develop optimal algorithms for solving this problem in a very general setting. Next, I will describe work on how to escape pessimism traps -- a phenomenon in which agents are influenced by their predecessors to engage in less-ambitious goals. We provide a mathematical formalism in which to study this concept that was first identified by philosophers. Then, we provide an algorithmic intervention to sustainably shift communities out of these traps. I will conclude the talk with some reflections on how these two styles of work can influence each other and my plans for future work in these areas. Kavya Ravichandran is a PhD candidate at Toyota Technological Institute at Chicago (TTIC), advised by Avrim Blum. She works on machine learning theory and algorithmic decision-making, recently focused on multi-armed bandits and social learning. Prior to TTIC, she completed her MEng and S.B. degrees at MIT, where she worked on distribution property testing. She has been recognized as a Rising Star in ISyE-MS&E-IOER. Kavya also enjoys getting young students excited by math and computer science and to that end has mentored Girls Who Code clubs in Chicago. Milstein 912 & Zoom Barnard College barnard-admin@digitalpulp.com America/New_York public
Campus Map

Speaker: Kavya Ravichandran (Toyota Technological Institute at Chicago)

Title: Sequential and Social Decision-Making: Improving Multi-Armed Bandits and Pessimism Traps

The seminar will be available for in-person and Zoom participation. To participate online, please email inquiry-cs@barnard.edu to receive the Zoom link.

We are often faced with decisions that require us to invest effort before reaping reward — for instance, persevering through higher education or starting a business. In this talk, I will share my recent work on theoretical models for making such decisions based on (1) one’s interaction with the environment and (2) decisions of others in one’s community. First, I will discuss the improving multi-armed bandits problem, in which an agent is deciding between k different options, each of which has more reward the more they interact with it. The agent's goal is to maximize their total reward. We develop optimal algorithms for solving this problem in a very general setting. Next, I will describe work on how to escape pessimism traps -- a phenomenon in which agents are influenced by their predecessors to engage in less-ambitious goals. We provide a mathematical formalism in which to study this concept that was first identified by philosophers. Then, we provide an algorithmic intervention to sustainably shift communities out of these traps. I will conclude the talk with some reflections on how these two styles of work can influence each other and my plans for future work in these areas.

Kavya Ravichandran is a PhD candidate at Toyota Technological Institute at Chicago (TTIC), advised by Avrim Blum. She works on machine learning theory and algorithmic decision-making, recently focused on multi-armed bandits and social learning. Prior to TTIC, she completed her MEng and S.B. degrees at MIT, where she worked on distribution property testing. She has been recognized as a Rising Star in ISyE-MS&E-IOER. Kavya also enjoys getting young students excited by math and computer science and to that end has mentored Girls Who Code clubs in Chicago.

Computer Science