Mahalakshmi Sabanayagam

According to our database, Mahalakshmi Sabanayagam authored at least 19 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

The Quantization Benefits of Residual-Free Transformers.

Yiping Ji, Mahalakshmi Sabanayagam, Peyman Moghadam, Hemanth Saratchandran, Simon Lucey

CoRR, May, 2026

Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks.

Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

CoRR, May, 2026

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning.

Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann

CoRR, April, 2026

2025

Robustness Certificates for Neural Networks against Adversarial Attacks.

Sara Taheri, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Majid Zamani

CoRR, December, 2025

Why does your graph neural network fail on some graphs? Insights from exact generalisation error.

Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

CoRR, September, 2025

Generalization Certificates for Adversarially Robust Bayesian Linear Regression.

Mahalakshmi Sabanayagam, Russell Tsuchida, Cheng Soon Ong, Debarghya Ghoshdastidar

CoRR, February, 2025

Robust Machine Learning from the Theory of Overparameterization: Neural Tangents and Tensorization.

Mahalakshmi Sabanayagam

PhD thesis, 2025

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks.

Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann

Trans. Mach. Learn. Res., 2025

Exact Certification of (Graph) Neural Networks Against Label Poisoning.

Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections.

Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet, Debarghya Ghoshdastidar

Trans. Mach. Learn. Res., 2024

Cluster Specific Representation Learning.

Mahalakshmi Sabanayagam, Omar Al-Dabooni, Pascal Mattia Esser

CoRR, 2024

2023

Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel.

Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar

Trans. Mach. Learn. Res., 2023

Fast Adaptive Test-Time Defense with Robust Features.

Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet, Debarghya Ghoshdastidar

CoRR, 2023

Kernels, Data & Physics.

Francesco Cagnetta, Deborah Oliveira, Mahalakshmi Sabanayagam, Nikolaos Tsilivis, Julia Kempe

CoRR, 2023

Unveiling the Hessian's Connection to the Decision Boundary.

Mahalakshmi Sabanayagam, Freya Behrens, Urte Adomaityte, Anna Dawid

CoRR, 2023

Improved Representation Learning Through Tensorized Autoencoders.

Pascal Mattia Esser, Satyaki Mukherjee, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Representation Power of Graph Convolutions : Neural Tangent Kernel Analysis.

Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar

CoRR, 2022

Graphon based Clustering and Testing of Networks: Algorithms and Theory.

Mahalakshmi Sabanayagam, Leena Chennuru Vankadara, Debarghya Ghoshdastidar

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

New Insights into Graph Convolutional Networks using Neural Tangent Kernels.

Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar

CoRR, 2021