96 citations · 298 across the 54 of their papers we have counts for
31 papers · 1 filter
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…
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…
Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization
Pascal Esser, Maximilian Fleissner, Debarghya Ghoshdastidar
Representation learning from unlabeled data has been extensively studied in statistics, data science and signal processing with a rich literature on techniques for dimension reduct…
Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
Maedeh Zarvandi, Michael Timothy, Theresa Wasserer +1
Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanat…
Generalization Certificates for Adversarially Robust Bayesian Linear Regression
Mahalakshmi Sabanayagam, Russell Tsuchida, Cheng Soon Ong +1
Adversarial robustness of machine learning models is critical to ensuring reliable performance under data perturbations. Recent progress has been on point estimators, and this pape…
Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters
Yaomengxi Han, Debarghya Ghoshdastidar
Learning sparse parity functions has become a theoretical testbed for studying feature learning in neural networks. However, existing analyses primarily focus on Feed-Forward Neura…
Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit
Martin Eppert, Satyaki Mukherjee, Debarghya Ghoshdastidar
Projection Pursuit is a classic exploratory technique for finding interesting projections of a dataset. We propose a method for recovering projections containing either Imbalanced…
A Probabilistic Model for Non-Contrastive Learning
Maximilian Fleissner, Pascal Esser, Debarghya Ghoshdastidar
Self-supervised learning (SSL) aims to find meaningful representations from unlabeled data by encoding semantic similarities through data augmentations. Despite its current popular…
Exact Certification of (Graph) Neural Networks Against Label Poisoning
Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann +1
Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustn…
Infinite Width Limits of Self Supervised Neural Networks
Maximilian Fleissner, Gautham Govind Anil, Debarghya Ghoshdastidar
The NTK is a widely used tool in the theoretical analysis of deep learning, allowing us to look at supervised deep neural networks through the lenses of kernel regression. Recently…
A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
Shlomo Libo Feigin, Maximilian Fleissner, Debarghya Ghoshdastidar
Data augmentations play an important role in the recent success of self-supervised learning (SSL). While augmentations are commonly understood to encode invariances between differe…
Explainable Clustering of Mixture Models
Maximilian Fleissner, Maedeh Zarvandi, Debarghya Ghoshdastidar
The explainable clustering problem was first posed by Moshkovitz et al. (ICML 2020) and studies how well an axis-aligned decision tree with leaves can approximate a given clust…
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…
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
Gautham Govind Anil, Pascal Esser, Debarghya Ghoshdastidar
Contrastive learning is a paradigm for learning representations from unlabelled data that has been highly successful for image and text data. Several recent works have examined con…
Explaining Kernel Clustering via Decision Trees
Maximilian Fleissner, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
Despite the growing popularity of explainable and interpretable machine learning, there is still surprisingly limited work on inherently interpretable clustering methods. Recently,…
On the Convergence of Gradient Descent for Large Learning Rates
Alexandru Crăciun, Debarghya Ghoshdastidar
A vast literature on convergence guarantees for gradient descent and derived methods exists at the moment. However, a simple practical situation remains unexplored: when a fixed st…
Non-Parametric Representation Learning with Kernels
Pascal Esser, Maximilian Fleissner, Debarghya Ghoshdastidar
Unsupervised and self-supervised representation learning has become popular in recent years for learning useful features from unlabelled data. Representation learning has been most…
Representation Learning Dynamics of Self-Supervised Models
Pascal Esser, Satyaki Mukherjee, Debarghya Ghoshdastidar
Self-Supervised Learning (SSL) is an important paradigm for learning representations from unlabelled data, and SSL with neural networks has been highly successful in practice. Howe…
Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections
Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet +1
Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional train…
Wasserstein Projection Pursuit of Non-Gaussian Signals
Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar
We consider the general dimensionality reduction problem of locating in a high-dimensional data cloud, a -dimensional non-Gaussian subspace of interesting features. We use a pro…
Improved Representation Learning Through Tensorized Autoencoders
Pascal Mattia Esser, Satyaki Mukherjee, Mahalakshmi Sabanayagam +1
The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster struct…
A Revenue Function for Comparison-Based Hierarchical Clustering
Aishik Mandal, Michaël Perrot, Debarghya Ghoshdastidar
Comparison-based learning addresses the problem of learning when, instead of explicit features or pairwise similarities, one only has access to comparisons of the form: \emph{Objec…
Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel
Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar
The fundamental principle of Graph Neural Networks (GNNs) is to exploit the structural information of the data by aggregating the neighboring nodes using a `graph convolution' in c…
Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks
Pascal Mattia Esser, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
In recent years, several results in the supervised learning setting suggested that classical statistical learning-theoretic measures, such as VC dimension, do not adequately explai…