Siddharth Mitra

I am a PhD student at Yale University in the Department of Computer Science where I am lucky to be advised by Andre Wibisono.

My research focuses on the design and analysis of algorithms for sampling and optimization.

Prior to this, I was an undergraduate and masters student at the Chennai Mathematical Institute as well as a visiting student at the Indian Institute of Science, Bangalore. During this time, I worked with Aditya Gopalan, Himanshu Tyagi, and KV Subrahmanyam.

I can be reached at siddharth.mitra <at> yale <dot> edu.

My Google Scholar.

Research

On the Mixing Time of Unadjusted Hamiltonian Monte Carlo in KL Divergence and Rényi Divergence via One-shot Couplings
(α-β) Nawaf Bou-Rabee, Siddharth Mitra, and Andre Wibisono
Preliminary version at DynaFront 2025.

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of Φ-Mutual Information [arXiv]
(α-β) Jiaming Liang, Siddharth Mitra, and Andre Wibisono
COLT 2025.

On the Convergence of Min-Max Langevin Dynamics and Algorithm [arXiv]
(α-β) Yang Cai, Siddharth Mitra, Xiuyuan Wang, and Andre Wibisono
COLT 2025.

Fast Convergence of Φ-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler [arXiv]
(α-β) Siddharth Mitra and Andre Wibisono
ALT 2025.

Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning [arXiv]
(α-β) Amin Karbasi, Nikki Kuang, Yian Ma, and Siddharth Mitra
ICML 2023.

Submodular + Concave [arXiv]
Siddharth Mitra, Moran Feldman, and Amin Karbasi
NeurIPS 2021.

On Adaptivity in Information-constrained Online Learning [arXiv]
Siddharth Mitra and Aditya Gopalan
AAAI 2020. Preliminary version at OPT 2019 [OPT Poster].