About Me

I am currently doing my PhD in Statistical Physics at IIT Bombay. My academic background lies at the intersection of physics, computation, and applied mathematics—but I am equally passionate about Machine Learning and Financial Engineering.

My research spans mean-field theory of active matter systems and data-driven discovery of hydrodynamic equations using machine learning—combining deep physical intuition with modern computational tools.

Outside the lab, I actively explore quantitative finance, stochastic modelling, and reinforcement learning, with an eye toward applying these methods in industry.


Current Projects

01 / 02

Mean Field Models for Non-Equilibrium Systems

Modeling active matter using mean-field theory. Involves deriving and numerically solving complex nonlinear PDEs governing collective behaviour far from thermodynamic equilibrium—combining deep physical intuition with computational rigour.

Active Matter PDE Numerics Statistical Mechanics Nonlinear Dynamics

02 / 02

Data-Driven Discovery of Hydrodynamic Equations

Using machine learning to predict coarse-grained hydrodynamic equations directly from particle-level simulations. This work sits at the intersection of physics-informed ML, statistical mechanics, and dynamical systems theory.

SINDy Physics-Informed ML Coarse-Graining Simulation

Projects

  • An implementation of Mean Field Game theory to study systemic risk in an interconnected network of banks. Models how local interactions between financial agents propagate into macro-level instability—bridging statistical physics with financial mathematics.

  • A Python implementation of the Gillespie algorithm for exact stochastic simulation of chemical kinetics and reaction networks. Useful for modelling discrete stochastic processes in biology and physics where continuous approximations fail.


Career Interests

⚗️

Quantitative Research

Applying stochastic calculus and statistical modelling to financial markets. Derivatives pricing, risk analytics, and systematic strategy development.

📊

Data Science

Leveraging high-dimensional data, Bayesian inference, and ML to extract signal from noise—in physical simulations or real-world datasets.

🤖

Financial Engineering

Deepened through IE612—derivatives, risk models, and quantitative finance frameworks, building on stochastic calculus from statistical mechanics.


Relevant Coursework

Financial Engineering IE612
AI and Data Science PH227
Markov Decision Processes IE708
Reinforcement Learning Algorithms IE620
Advanced Statistical Mechanics PH
Stochastic Calculus (self-study)

RL Roadmap

Currently exploring Reinforcement Learning and its applications in quantitative modelling. Following the David Silver lecture series and implementing key algorithms in Python from scratch.

The goal: build a solid theoretical foundation—Bellman equations, policy gradients, Q-learning— and connect these ideas to sequential decision-making in financial contexts.

📘 View on GitHub ↗
Markov Decision Processes
Dynamic Programming
Monte Carlo Methods
TD Learning & Q-Learning
Function Approximation
Policy Gradient Methods
Actor-Critic Architectures
Deep RL Applications

55% complete · David Silver series


Let's connect

Open to conversations about quant research roles, data science positions, and collaborative research. Mumbai-based, open to relocation.