activity
20242026
collaborators

9 papers

cs.LG2026

The Quantization Benefits of Residual-Free Transformers

Yiping Ji, Mahalakshmi Sabanayagam, Peyman Moghadam +2

Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across accelerators. Low-bit quantizati…

stat.ME2026

Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks

Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

Graph Neural Networks (GNN) are currently the most popular approach for learning and prediction on graph-structured data and are deployed in various fields, from social network ana…

cs.LG2026

Robustness Certificates for Neural Networks Against Data Poisoning and Evasion Attacks

Sara Taheri, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar +1

The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade…

cs.LG2026

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

Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam +2

Label-flipping attacks, which corrupt training labels to induce misclassifications at inference, remain a major threat to supervised learning models. This drives the need for robus…

stat.ML2026

Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)

Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what…

cs.LG2025

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

Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar +1

Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to i…