dheerajbaby[at]gmail[.]com LinkedIn Google Scholar

I am an Applied Scientist at Amazon. I obtained my PhD in Computer Science from UC Santa Barbara where I was fortunate to be advised by Prof. Yu-Xiang Wang. I am interested in developing theory and algorithms for empirically motivated machine learning problems. My current research interests include Learning in non-stationary environments, Domain Adaptation and Multi-Task Learning. I received my Bachelors and Masters degrees in Electrical Engineering from Indian Institute of Technology, Chennai.

Publications

• Dheeraj Baby, Yifei Tang, Hieu Duy Nguyen, Yu-Xiang Wang, Rohit Pyati, "Adaptive Estimation and Learning under Temporal Distribution Shift", ICML 2025 [pdf]

• Sunil Madhow, Dheeraj Baby, Yu-Xiang Wang "AKORN: Adaptive Knots generated Online for RegressioN splines", ICML 2025

• Dheeraj Baby, Boran Han, Shuai Zhang, Cuixiong Hu, Bernie Wang, Yu-Xiang Wang "Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach", AISTATS 2025 [pdf]

• Dheeraj Baby* and Soumyabrata Pal* "Online Matrix Completion: A Collaborative Approach with Hott Items", ICML 2024 [pdf]

• Ruihan Wu, Siddhartha Datta, Yi Su, Dheeraj Baby, Yu-Xiang Wang, Kilian Q. Weinberger "Online Feature Updates Improve Online (Generalized) Label Shift Adaptation", NeurIPS 2024 [pdf]

• Dheeraj Baby*, Saurabh Garg*, Tzu-Ching Yen*, Sivaraman Balakrishnan, Zachary Lipton and Yu-Xiang Wang "Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms", NeurIPS 2023 [pdf], Spotlight Presentation

• Dheeraj Baby and Yu-Xiang Wang "Second Order Path Variationals in Non-Stationary Online Learning", AISTATS 2023 [pdf]

• Dheeraj Baby, Aniket Das, Dheeraj Nagaraj and Praneeth Netrapalli, "Near Optimal Heteroscedastic Regression with Symbiotic Learning", COLT 2023 [pdf]

• Dheeraj Baby*, Jianyu Xu* and Yu-Xiang Wang "Non-stationary Contextual Pricing with Safety Constraints", TMLR 2022

• Dheeraj Baby and Yu-Xiang Wang "Optimal Dynamic Regret in LQR Control", NeurIPS 2022 [pdf]

• Dheeraj Baby and Yu-Xiang Wang "Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond", AISTATS 2022 [pdf]

• Dheeraj Baby and Yu-Xiang Wang "Optimal Dynamic Regret in Exp-Concave Online Learning", COLT 2021 [pdf], Best Student Paper Award

• Dheeraj Baby, Xuandong Zhao and Yu-Xiang Wang "An Optimal Reduction of TV-Denoising to Adaptive Online Learning", AISTATS 2021 [pdf]

• Dheeraj Baby and Yu-Xiang Wang "Adaptive Online Estimation of Piecewise Polynomial Trends", NeurIPS 2020 [pdf]

• Dheeraj Baby and Yu-Xiang Wang "Online Forecasting of Total-Variation-Bounded Sequences", NeurIPS 2019 [pdf] [video]

• Jason R. Baumgartner, Robert L. Kanzelman, Pradeep Kumar Nalla, Raj Kumar Gajavelly, Dheeraj Baby "Initial-state and next-state value folding", US Patent [US10621297B1]
  (* = Equal contribution)

Industry and Academic Experience

• Reviewer at ICML19,20,21,23,25 JMLR21,22,23 AISTATS22,23, ICLR24

• Intern, AWS AI Labs, AWS Deep Engine Science, Aug 2023 - Nov 2023

• Intern, Google Research, Machine Learning and Optimization group, Jun 2022 - Sept 2022

• Intern, AWS AI Labs, Time Series forecasting group, Jun 2020 - Sept 2020

• Software developer, IBM Bangalore, India, 2016-2018