Debarghya Ghoshdastidar

85 papers A* 16A 6B 2Journal 59Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Gaussian Process Limit Reveals Structural Benefits of Graph Transformers. CoRR Nil Ayday, Lingchu Yang, Debarghya Ghoshdastidar
2026	J	`jnl`	Nonparametric Kernel Clustering with Bandit Feedback. CoRR Victor Thuot, Sebastian Vogt, Debarghya Ghoshdastidar, Nicolas Verzelen
2026	J	`jnl`	Recovering Imbalanced Clusters via gradient-based projection pursuit. J. Multivar. Anal. Martin Eppert, Satyaki Mukherjee, Debarghya Ghoshdastidar
2026	J	`jnl`	Wasserstein projection pursuit of non-Gaussian signals. J. Multivar. Anal. Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar
2025	J	`jnl`	A Probabilistic Model for Self-Supervised Learning. CoRR Maximilian Fleissner, Pascal Mattia Esser, Debarghya Ghoshdastidar
2025	J	`jnl`	Attention Learning is Needed to Efficiently Learn Parity Function. CoRR Yaomengxi Han, Debarghya Ghoshdastidar
2025	A*	`conf`	Exact Certification of (Graph) Neural Networks Against Label Poisoning. ICLR Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar
2025	J	`jnl`	Generalization Certificates for Adversarially Robust Bayesian Linear Regression. CoRR Mahalakshmi Sabanayagam, Russell Tsuchida, Cheng Soon Ong, Debarghya Ghoshdastidar
2025	J	`jnl`	Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders. CoRR Jonghyun Ham, Maximilian Fleissner, Debarghya Ghoshdastidar
2025	A	`conf`	Infinite Width Limits of Self Supervised Neural Networks. AISTATS Maximilian Fleissner, Gautham Govind Anil, Debarghya Ghoshdastidar
2025	J	`jnl`	Interpretable Kernel Representation Learning at Scale: A Unified Framework Utilizing Nyström Approximation. CoRR Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar
2025	J	`jnl`	Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations. CoRR Alexandru Craciun, Debarghya Ghoshdastidar
2025	J	`jnl`	Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks. Trans. Mach. Learn. Res. Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann
2025	J	`jnl`	Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit. CoRR Martin Eppert, Satyaki Mukherjee, Debarghya Ghoshdastidar
2025	J	`jnl`	Robustness Certificates for Neural Networks against Adversarial Attacks. CoRR Sara Taheri, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Majid Zamani
2025	J	`jnl`	Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization. CoRR Pascal Mattia Esser, Maximilian Fleissner, Debarghya Ghoshdastidar
2025	J	`jnl`	Tight PAC-Bayesian Risk Certificates for Contrastive Learning. SIAM J. Math. Data Sci. Anna Van Elst, Debarghya Ghoshdastidar
2025	A*	`conf`	When Can We Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis? AAAI Gautham Govind Anil, Pascal Mattia Esser, Debarghya Ghoshdastidar
2025	J	`jnl`	Why does your graph neural network fail on some graphs? Insights from exact generalisation error. CoRR Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
2024	J	`jnl`	Data Augmentations Go Beyond Encoding Invariances: A Theoretical Study on Self-Supervised Learning. CoRR Shlomo Libo Feigin, Maximilian Fleissner, Debarghya Ghoshdastidar
2024	J	`jnl`	Decision Trees for Interpretable Clusters in Mixture Models and Deep Representations. CoRR Maximilian Fleissner, Maedeh Zarvandi, Debarghya Ghoshdastidar
2024	J	`jnl`	Exact Certification of (Graph) Neural Networks Against Label Poisoning. CoRR Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar
2024	A*	`conf`	Explaining Kernel Clustering via Decision Trees. ICLR Maximilian Fleissner, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2024	J	`jnl`	Explaining Kernel Clustering via Decision Trees. CoRR Maximilian Fleissner, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2024	J	`jnl`	Infinite Width Limits of Self Supervised Neural Networks. CoRR Maximilian Fleissner, Gautham Govind Anil, Debarghya Ghoshdastidar
2024	A*	`conf`	Non-parametric Representation Learning with Kernels. AAAI Pascal Mattia Esser, Maximilian Fleissner, Debarghya Ghoshdastidar
2024	J	`jnl`	On the Stability of Gradient Descent for Large Learning Rate. CoRR Alexandru Craciun, Debarghya Ghoshdastidar
2024	J	`jnl`	Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks. CoRR Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann
2024	J	`jnl`	Representation Learning Dynamics of Self-Supervised Models. Trans. Mach. Learn. Res. Pascal Mattia Esser, Satyaki Mukherjee, Debarghya Ghoshdastidar
2024	J	`jnl`	Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections. Trans. Mach. Learn. Res. Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet, Debarghya Ghoshdastidar
2024	J	`jnl`	Tight PAC-Bayesian Risk Certificates for Contrastive Learning. CoRR Anna Van Elst, Debarghya Ghoshdastidar
2024	J	`jnl`	When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis? CoRR Gautham Govind Anil, Pascal Mattia Esser, Debarghya Ghoshdastidar
2023	J	`jnl`	A Revenue Function for Comparison-Based Hierarchical Clustering. Trans. Mach. Learn. Res. Aishik Mandal, Michaël Perrot, Debarghya Ghoshdastidar
2023	J	`jnl`	Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel. Trans. Mach. Learn. Res. Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar
2023	J	`jnl`	Fast Adaptive Test-Time Defense with Robust Features. CoRR Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet, Debarghya Ghoshdastidar
2023	A	`conf`	Improved Representation Learning Through Tensorized Autoencoders. AISTATS Pascal Mattia Esser, Satyaki Mukherjee, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
2023	J	`jnl`	Non-Parametric Representation Learning with Kernels. CoRR Pascal Mattia Esser, Maximilian Fleissner, Debarghya Ghoshdastidar
2023	J	`jnl`	Representation Learning Dynamics of Self-Supervised Models. CoRR Pascal Mattia Esser, Satyaki Mukherjee, Debarghya Ghoshdastidar
2023	J	`jnl`	Wasserstein Projection Pursuit of Non-Gaussian Signals. CoRR Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar
2022	J	`jnl`	A Consistent Estimator for Confounding Strength. CoRR Luca Rendsburg, Leena Chennuru Vankadara, Debarghya Ghoshdastidar, Ulrike von Luxburg
2022	J	`jnl`	A Revenue Function for Comparison-Based Hierarchical Clustering. CoRR Aishik Mandal, Michaël Perrot, Debarghya Ghoshdastidar
2022	A	`conf`	Causal forecasting: generalization bounds for autoregressive models. UAI Leena Chennuru Vankadara, Philipp Michael Faller, Michaela Hardt, Lenon Minorics, Debarghya Ghoshdastidar, Dominik Janzing
2022	A*	`conf`	Graphon based Clustering and Testing of Networks: Algorithms and Theory. ICLR Mahalakshmi Sabanayagam, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2022	J	`jnl`	Improved Representation Learning Through Tensorized Autoencoders. CoRR Pascal Mattia Esser, Satyaki Mukherjee, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
2022	A*	`conf`	Interpolation and Regularization for Causal Learning. NeurIPS Leena Chennuru Vankadara, Luca Rendsburg, Ulrike von Luxburg, Debarghya Ghoshdastidar
2022	J	`jnl`	Interpolation and Regularization for Causal Learning. CoRR Leena Chennuru Vankadara, Luca Rendsburg, Ulrike von Luxburg, Debarghya Ghoshdastidar
2022	J	`jnl`	Representation Power of Graph Convolutions : Neural Tangent Kernel Analysis. CoRR Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar
2021	J	`jnl`	Causal Forecasting: Generalization Bounds for Autoregressive Models. CoRR Leena C. Vankadara, Philipp Michael Faller, Lenon Minorics, Debarghya Ghoshdastidar, Dominik Janzing
2021	J	`jnl`	Graphon based Clustering and Testing of Networks: Algorithms and Theory. CoRR Mahalakshmi Sabanayagam, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2021	—	`conf`	Improvement on Incremental Spectral Clustering. LWDA Nil Ayday, Debarghya Ghoshdastidar
2021	A*	`conf`	Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks. NeurIPS Pascal Mattia Esser, Leena C. Vankadara, Debarghya Ghoshdastidar
2021	J	`jnl`	Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks. CoRR Pascal Mattia Esser, Leena C. Vankadara, Debarghya Ghoshdastidar
2021	J	`jnl`	New Insights into Graph Convolutional Networks using Neural Tangent Kernels. CoRR Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar
2021	A	`conf`	Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models. AISTATS Leena C. Vankadara, Sebastian Bordt, Ulrike von Luxburg, Debarghya Ghoshdastidar
2021	J	`jnl`	Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models. CoRR Leena C. Vankadara, Sebastian Bordt, Ulrike von Luxburg, Debarghya Ghoshdastidar
2020	A*	`conf`	Near-Optimal Comparison Based Clustering. NeurIPS Michaël Perrot, Pascal Mattia Esser, Debarghya Ghoshdastidar
2020	J	`jnl`	Near-Optimal Comparison Based Clustering. CoRR Michaël Perrot, Pascal Mattia Esser, Debarghya Ghoshdastidar
2020	A	`conf`	On the optimality of kernels for high-dimensional clustering. AISTATS Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2019	A*	`conf`	Foundations of Comparison-Based Hierarchical Clustering. NeurIPS Debarghya Ghoshdastidar, Michaël Perrot, Ulrike von Luxburg
2019	J	`jnl`	On the optimality of kernels for high-dimensional clustering. CoRR Leena Chennuru Vankadara, Debarghya Ghoshdastidar
2018	J	`jnl`	Foundations of Comparison-Based Hierarchical Clustering. CoRR Debarghya Ghoshdastidar, Michaël Perrot, Ulrike von Luxburg
2018	A*	`conf`	Practical Methods for Graph Two-Sample Testing. NeurIPS Debarghya Ghoshdastidar, Ulrike von Luxburg
2018	J	`jnl`	Practical methods for graph two-sample testing. CoRR Debarghya Ghoshdastidar, Ulrike von Luxburg
2017	J	`jnl`	Comparison Based Nearest Neighbor Search. CoRR Siavash Haghiri, Debarghya Ghoshdastidar, Ulrike von Luxburg
2017	A	`conf`	Comparison-Based Nearest Neighbor Search. AISTATS Siavash Haghiri, Debarghya Ghoshdastidar, Ulrike von Luxburg
2017	A*	`conf`	Two-Sample Tests for Large Random Graphs Using Network Statistics. COLT Debarghya Ghoshdastidar, Maurilio Gutzeit, Alexandra Carpentier, Ulrike von Luxburg
2017	J	`jnl`	Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques. J. Mach. Learn. Res. Debarghya Ghoshdastidar, Ambedkar Dukkipati
2016	J	`jnl`	Learning With Jensen-Tsallis Kernels. IEEE Trans. Neural Networks Learn. Syst. Debarghya Ghoshdastidar, Ajay P. Adsul, Ambedkar Dukkipati
2016	B	`conf`	Mixture modeling with compact support distributions for unsupervised learning. IJCNN Ambedkar Dukkipati, Debarghya Ghoshdastidar, Jinu Krishnan
2016	J	`jnl`	Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques. CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati
2015	A*	`conf`	A Provable Generalized Tensor Spectral Method for Uniform Hypergraph Partitioning. ICML Debarghya Ghoshdastidar, Ambedkar Dukkipati
2015	A*	`conf`	Spectral Clustering Using Multilinear SVD: Analysis, Approximations and Applications. AAAI Debarghya Ghoshdastidar, Ambedkar Dukkipati
2014	—	`conf`	Consistency of Spectral Partitioning of Uniform Hypergraphs under Planted Partition Model. NIPS Debarghya Ghoshdastidar, Ambedkar Dukkipati
2014	J	`jnl`	Newton-based stochastic optimization using q-Gaussian smoothed functional algorithms. Autom. Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
2014	J	`jnl`	Smoothed Functional Algorithms for Stochastic Optimization Using ACM Trans. Model. Comput. Simul. Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
2014	A*	`conf`	Spectral Clustering with Jensen-Type Kernels and Their Multi-point Extensions. CVPR Debarghya Ghoshdastidar, Ambedkar Dukkipati, Ajay P. Adsul, Aparna S. Vijayan
2014	J	`jnl`	Spectral Clustering with Jensen-type kernels and their multi-point extensions. CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati, Ajay P. Adsul, Aparna S. Vijayan
2013	A*	`conf`	Generative Maximum Entropy Learning for Multiclass Classification. ICDM Ambedkar Dukkipati, Gaurav Pandey, Debarghya Ghoshdastidar, Paramita Koley, D. M. V. Satya Sriram
2013	J	`jnl`	Newton based Stochastic Optimization using q-Gaussian Smoothed Functional Algorithms. CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
2013	A*	`conf`	On Power-Law Kernels, Corresponding Reproducing Kernel Hilbert Space and Applications. AAAI Debarghya Ghoshdastidar, Ambedkar Dukkipati
2012	J	`jnl`	Maximum Entropy with Maximum J-Divergence Discrimination for Text Classification CoRR D. M. V. Satya Sriram, Gaurav Pandey, Debarghya Ghoshdastidar, Ambedkar Dukkipati, M. Narasimha Murty
2012	J	`jnl`	On q-Gaussian kernel and its Reproducing Kernel Hilbert Space CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati
2012	J	`jnl`	Smoothed Functional Algorithms for Stochastic Optimization using q-Gaussian Distributions. CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
2012	J	`jnl`	q-Gaussian based Smoothed Functional Algorithm for Stochastic Optimization CoRR Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
2012	B	`conf`	q-Gaussian based Smoothed Functional algorithms for stochastic optimization. ISIT Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar