Mayank Shrivastava

Hi! I am a master’s in Computer Science student at the University of Illinois at Urbana Champaign. I am advised by Dr. Arindam Banerjee. Currently, I am working on tackling distribution shifts in ML models, Federated Learning and Differential Privacy.

Before joining UIUC, I was a research assistant with Prof. Jonathan Scarlett at NUS, where I worked on Multi-Armed Bandits. Previously, I spent an year working in the AI R&D Lab at Samsung Research and Development Headquarters in South Korea on Speech Processing and Language Models.

I completed my undergrad from IIT Kanpur in Electrical Engineering. I worked with Dr. Himanshu Tyagi at IISc, Dr.Vipul Arora at IITK, and Dr. Minseok Kwon at Samsung Electronics during my undergraduate years.

news

Mar'24	Paper on Dimension-free federated learning accepted in BGPT Workshop, ICLR’4.
Jun'23	Started working as a Teaching Assistant for CS411 Databases (Summer 2023)!
Feb'23	Paper on Max-Quantile Bandits accepted in ALT’23.
Jan'23	Started working as a Teaching Assistant for CS124 (Intro to Programming in Java) !
Oct'22	Started working as a Teaching Assistant for CS412 (Data Mining) !
Aug'22	Joined Master’s, Computer Science (thesis track) program at University of Illinois, Urbana-Champaign!
Apr'22	Joined Prof. Jonathan Scarlett’s lab at NUS as a Research Assistant.
Oct'20	Joined the Automatic Speech Recognition team at Samsung Electronics, South Korea as a MLE !
May'20	Started as a Research Associate at IISc Bangalore with Prof. Himanshu Tyagi.
Apr'20	Graduated with a major in Electrical Engineering from IIT Kanpur .

selected publications

2023

Max-Quantile Grouped Infinite-Arm Bandits

Ivan Lau, Yan Hao Ling, Mayank Shrivastava, and 1 more author

In Proceedings of The 34th International Conference on Algorithmic Learning Theory, 20 feb–23 feb 2023

Abs PDF

In this paper, we consider a bandit problem in which there are a number of groups each consisting of infinitely many arms. Whenever a new arm is requested from a given group, its mean reward is drawn from an unknown reservoir distribution (different for each group), and the uncertainty in the arm’s mean reward can only be reduced via subsequent pulls of the arm. The goal is to identify the infinite-arm group whose reservoir distribution has the highest (1-α)-quantile (e.g., median if α= \frac12), using as few total arm pulls as possible. We introduce a two-step algorithm that first requests a fixed number of arms from each group and then runs a finite-arm grouped max-quantile bandit algorithm. We characterize both the instance-dependent and worst-case regret, and provide a matching lower bound for the latter, while discussing various strengths, weaknesses, algorithmic improvements, and potential lower bounds associated with our instance-dependent upper bounds.