I am a Ph.D. student in Machine Learning theory advised by Prof. Debarghya Ghoshdastidar at the Theoretical Foundations of Artificial Intelligence group, Technical University of Munich since August 2021. My research focuses on the theory of deep learning primarily in understanding the connection of deep networks to kernel machines and in studying its adversarial robustness. Recently, I visited Dr. Cheng Soon Ong at CSIRO Australia and worked along with Dr. Russell Tsuchida on adversarial robustness of probabilistic models. Earlier, I visited Prof. Julia Kempe at New York University and focused on studying adversarial training. I am also interested in graph based learning and statistical learning theory.
Previously, I did Masters of Science in Informatics at Technical University of Munich and bachelors in Computer Science & Engineering from National Institute of Technology, Trichy, India. Between my undergraduate and graduate studies, I spent a little over 3 years at Adobe Systems, India as a Computer Scientist.
Research Interests
- Theory of deep learning and robustness of neural networks and probabilistic models
- Machine learning on graphs
- Statistical learning theory
Recent News
April 23 – 28, 2025 | Excited to attend ICLR in Singapore! |
Feb 19 – 21, 2025 | Excited to give a talk on Certifying (Graph) Neural Networks against Data Poisoning using the Neural Tangent Kernel at understanding generalization in deep learning workshop at Burghausen! |
Feb 11, 2025 | Our paper Exact Certification of (Graph) Neural Networks Against Label Poisoning got accepted as a Spotlight (top 5.1%) at ICLR 2025 🎉 |
Dec 5, 2024 | Our paper Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks won the best paper award at AdvML-Frontiers@NeurIPS 2024 🎉 |
Nov 4, 2024 | Won 3rd price in EMCR talk at AI in Science Conference 2024, Canberra 🏆 |