Spandan Senapati
Spandan Senapati

Graduate student

Biography

I am a second year CS Ph.D. student in the Theory group at the University of Southern California, where I am fortunate to be advised by Prof. Haipeng Luo and Prof. Vatsal Sharan. I am broadly interested in online learning and statistical learning theory.

Previously, I was a research assistant in the Signal Processing in Networking (SPiN) lab, Indian Institute of Technology Kanpur (IITK), where I was advised by Prof. Ketan Rajawat. I am quite privileged to have collaborated with Prof. Rahul Vaze (Tata Institute of Fundamental Research) during this period.

Before that, I graduated from IITK with a Bachelor’s degree in Computer Science. I am very fortunate to have been supervised by Prof. Ketan Rajawat during my undergraduate.

I am always open to discussions on theoretical CS and math. As an aside, I am quite passionate about music and have been playing fingerstyle guitar for a while.

Download CV
Interests
  • Statistical Learning Theory
  • Online Learning Theory
  • Optimization
Education
  • Bachelor of Technology in Computer Science and Engineering (2018-2022)

    Indian Institute of Technology Kanpur

Publications and Preprints
(2024). Optimal Multiclass U-Calibration Error and Beyond. NeurIPS 2024.
(2024). Sharpened Lazy Incremental Quasi-Newton Method. AISTATS 2024.
(2023). Online convex optimization with switching cost and delayed gradients. IFIP Performance 2023. Full version: Performance Evaluation (PEVA), Extended abstract: ACM SIGMETRICS Performance Evaluation Review (PER).
(2023). Proximal Algorithms for Smoothed Online Convex Optimization with Predictions. IEEE Transactions on Signal Processing.