dheeraj(AT)ucsb(DOT)edu Google Scholar profile LinkedIn profile

About me

I am a fourth year PhD student in Computer Science department at UC Santa Barbara where I am fortunate to be advised by Prof. Yu-Xiang Wang. My research primarily focuses on developing parameter-free online learning algorithms that can optimally cope with non-stationarities present in the environment. Applications of my work include forecasting trends in Time Series, adaptive Total Variation denoising, non-stationary Multi Armed Bandits… (I am trying to expand this list :-). I received my Bachelors and Masters degrees in Electrical Engineering from Indian Institue of Technology, Chennai during 2016.

Publications

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

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

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

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

Industry and Academic Experience

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

• Reviewer at ICML19-21. Received top 33% reviewer award at ICML20.