Research Overview

The topics that pique my interest are flow-based generative modeling, LLMs, information-theoretic deep learning, and neural architecture search. I am interested in projects that are motivated by large-scale applications. I enjoy working with people from diverse disciplines. Some of my current projects are interdisciplinary, where I have collaborated with Engineers, Physicists, and Astronomers. I have developed and deployed statistical and machine-learning algorithms for large-scale data analysis. I am always looking for new areas in both theory and application to blend my experience to make meaningful contributions. 

Highlighted Publications

• "Spatiotemporal Forecasting of the Edge Localized Modes in Tokamak Plasmas using Neural Networks", Anirban Samaddar, Qian Gong, Sandeep Madireddy, Christopher Hansen, Semin Joung, David R. Smith, Yixuan Sun, Fatima Ebrahimi, Prasanna Balaprakash, Andrew Oakleigh Nelson. Machine Learning: Science and Technology (2025). (link)

• "Efficient Flow Matching using Latent Variables", Anirban Samaddar, Yixuan Sun, Viktor Nilsson, Sandeep Madireddy. International Conference on Artificial Intelligence and Statistics (AISTATS) (2026). (link)

• "REMEDI: Corrective Transformations for Improved Neural Entropy Estimation", Viktor Nilsson*, Anirban Samaddar*, Sandeep Madireddy, Pierre Nyquist. International Conference on Machine Learning (ICML) (2024). (link)

• "Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck", Anirban Samaddar, Sandeep Madireddy, Prasanna Balaprakash, Gustavo de los Campos, Tapabrata Maiti, and Ian Fischer. International Conference on Artificial Intelligence and Statistics (AISTATS) (2023). (link)

• "Bayesian Hierarchical Hypothesis Testing in Large-Scale Genome-Wide Association Study", Anirban Samaddar, Tapabrata Maiti, Gustavo de los Campos. Genetics (2024). (link)

__________

* equal contribution