Home  | Research | Groups | Suvrit Sra

Research Group Suvrit Sra


Link to website at TUM PI Matchmaking

Suvrit Sra

Prof. Dr.

Principal Investigator

Suvrit Sra

is Professor for Resource Aware Machine Learning at TU Munich.

He specializes in robust, reliable, and resource-efficient machine learning methods. His research focuses, in particular, on solving optimization problems for machine learning with multiple parameters. For example, these complex optimization problems are used in autonomous driving so that a car can reliably distinguish a sign from a person.

Team members @MCML

PostDocs

Link to website

Manish Krishan Lal

Dr.

PhD Students

Link to website

Pouria Fatemi

Link to website

Sai Niranjan Ramachandran

Link to website

Xuhui Zhang

Recent News @MCML

Link to MCML at ICML 2025

11.07.2025

MCML at ICML 2025

25 Accepted Papers (20 Main, and 5 Workshops)

Link to Humboldt Professorship for Stefanie Jegelka and Suvrit Sra

16.05.2024

Humboldt Professorship for Stefanie Jegelka and Suvrit Sra

Our PIs Were Honored With Germany's Most Highly Endowed Research Award

Publications @MCML

2025


[3] A* Conference
S. N. RamachandranM. K. LalS. Sra
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. To be published. Preprint available. URL

[2] A* Conference
P. Fatemi • E. Sharifian • M. H. Yassaee
A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL

[1]
A. BergmeisterM. K. LalS. JegelkaS. Sra
A projection-based framework for gradient-free and parallel learning.
Preprint (Jun. 2025). arXiv