Amartya Mukherjee

PhD student, Applied Mathematics, University of Waterloo

Intern, Borealis AI

Joined

January 2023

Names

Amartya Mukherjee (Preferred)

Emails

****@uwaterloo.ca (Confirmed)

Personal Links

Career & Education History

PhD student

Applied Mathematics, University of Waterloo (uwaterloo.ca)

2022 – 2027

Intern

Borealis AI (borealisai.com)

2024 – 2026

Advisors, Relations & Conflicts

Coauthor

Ruizhi Deng

2025 – Present

PhD Advisor

Jun Liu

2022 – 2027

Expertise

Diffusion Models

2024 – Present

Physics-Informed Machine Learning

2023 – Present

Publications

Almost Sure Convergence Analysis of Differentially Private Stochastic Gradient Methods
Amartya Mukherjee, Jun Liu
- CoRR 2025
- Readers: Everyone
ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
Amartya Mukherjee, Ruizhi Deng, He Zhao, Yuzhen Mao, Leonid Sigal, Frederick Tung
- Submitted to ICLR 2026
- Readers: Everyone
Manifold-Guided Stabilization of Nonlinear Dynamical Systems with Diffusion Models
Amartya Mukherjee, Thanin Quartz, Jun Liu
- ACC 2025
- Readers: Everyone
Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
Yiming Meng, Ruikun Zhou, Amartya Mukherjee, Maxwell Fitzsimmons, Christopher Song, Jun Liu
- ICML 2024 Poster
- Readers: Everyone
Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)
Amartya Mukherjee, Jun Liu
- Frontiers4LCD
- Readers: Everyone
Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs
Amartya Mukherjee, Jun Liu
- Frontiers4LCD
- Readers: Everyone

Amartya Mukherjee

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Almost Sure Convergence Analysis of Differentially Private Stochastic Gradient Methods

ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes

Manifold-Guided Stabilization of Nonlinear Dynamical Systems with Diffusion Models

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification

Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs

Co-Authors