Publications
Recent preprints / Papers in submission
-
A. van Elst, D. Ghoshdastidar. Tight PAC-Bayesian risk certificates for contrastive learning. [Preprint]
-
S. Mukherjee, S. S. Mukherjee, D. Ghoshdastidar. Wasserstein projection pursuit of non-Gaussian signals. Under review at Journal of Multivariate Analysis [Preprint] [PDF]
-
M. Eppert, S. Mukherjee, D. Ghoshdastidar. Recovering imbalanced clusters via gradient based projection pursuit. Under review at Journal of Multivariate Analysis [PDF]
-
A. Craciun, D. Ghoshdastidar. On the stability of gradient descent for large learning rate. [Preprint]
-
G. G. Anil, P. Esser, D. Ghoshdastidar. When can we approximate wide contrastive models with neural tangent kernels and principal component analysis? [Preprint]
Peer reviewed publications
-
L. Rendsburg, L. C. Vankadara, U. von Luxburg, D. Ghoshdastidar. A consistent estimator for confounding strength. Mathematical Statistics and Learning, 7 (3/4): 189-220, 2024. [Paper] [Preprint]
-
A. Singh, M. Sabanayagam, K. Muandet, D. Ghoshdastidar. Fast adaptive test-time defense with robust features. Transactions of Machine Learning, 2024. [Paper] [Preprint]
-
P. Esser, S. Mukherjee, D. Ghoshdastidar. Representation learning dynamics of self-supervised models. Transactions of Machine Learning, 2024. [Paper] [Preprint]
-
M. Fleissner, L. Vankadara, D. Ghoshdastidar. Explaining kernel clustering via decision trees. ICLR 2024 [Paper]
-
P. Esser, M. Fleissner, D. Ghoshdastidar. Non-parametric representation learning with kernels. AAAI 2024. [Paper] [Preprint]
-
M. Sabanayagam, P. Esser, D. Ghoshdastidar. Analysis of convolutions, non-linearity and depth in graph neural networks using neural tangent kernel. Transactions of Machine Learning Research, 2023. [Paper] [Preprint] [Code]
-
A. Mandal, M. Perrot, D. Ghoshdastidar. A revenue function for comparison-based hierarchical clustering. Transactions of Machine Learning Research, 2023 [Paper] [Preprint]
-
P. Esser, S. Mukherjee, M. Sabanayagam, D. Ghoshdastidar. Improved representation learning through tensorized autoencoders. AISTATS 2023. [Paper] [Preprint]
-
M. C. May, Z. Fang, M. Eitel, N. Stricker, D. Ghoshdastidar, G. Lanza. Graph-based prediction of missing KPIs through optimization and random forests for KPI Systems. Production Engineering, 2022. DOI:10.1007/s11740-022-01179-y [Paper]
-
L. Vankadara, L. Rendsburg, U. von Luxburg, D. Ghoshdastidar. Interpolation and regularization for causal learning. NeurIPS 2022 [Paper] [Preprint]
-
L. C. Vankadara, P. M. Faller, M. Hardt, L. Minorics, D. Ghoshdastidar, D. Janzing. Causal forecasting: Generalization bounds for autoregressive models. UAI 2022. [Paper] [Preprint] [Code]
-
M. Sabanayagam, L. C. Vankadara, D. Ghoshdastidar. Graphon based clustering and testing of networks: Algorithms and theory. ICLR 2022. [Paper] [Preprint] [Code]
-
S. Huber, S. H. Suyu, D. Ghoshdastidar, S. Taubenberger, V. Bonvin, J. H. H. Chan, M. Kromer, U. M. Noebauer, S. A. Sim, L. Leal-Taixé. HOLISMOKES -- VII. Time-delay measurement of strongly lensed Type Ia supernovae using machine learning. Astronomy & Astrophysics 2022. [Paper] [Preprint]
-
P. Esser, L. C. Vankadara, D. Ghoshdastidar. Learning theory can (sometimes) explain generalisation in graph neural networks. NeurIPS 2021 [Paper] [Preprint]
-
L. C. Vankadara, S. Bordt, U. von Luxburg, D. Ghoshdastidar. Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models. AISTATS 2021 [Paper]
-
M. Perrot, P. Esser, D. Ghoshdastidar. Near-optimal comparison based clustering. Neurips 2020 [Paper] [Preprint] [Code]
-
D. Ghoshdastidar, M. Gutzeit, A. Carpentier, U. Von Luxburg. Two-sample hypothesis testing for inhomogeneous random graphs. The Annals of Statistics, 48 (4): 2208-2229, 2020. [Paper] [Preprint]
-
L. C. Vankadara, D. Ghoshdastidar. On the optimality of kernels for high-dimensional clustering. AISTATS 2020. [Paper] [Preprint] [Video]
-
D. Ghoshdastidar, M. Perrot, U. Von Luxburg. Foundations of comparison-based hierarchical clustering. NeurIPS, 2019. [Paper] [Preprint] [Code]
-
D. Ghoshdastidar, U. Von Luxburg. Practical methods for graph two-sample testing. NeurIPS, 2018. [Paper] [Preprint] [Code]
-
D. Ghoshdastidar, M. Gutzeit, A. Carpentier, U. von Luxburg. Two-sample tests for large random graphs using network statistics. COLT, 2017. [Preprint]
-
D. Ghoshdastidar, A. Dukkipati. Uniform hypergraph partitioning: Provable tensor methods and sampling techniques. The Journal of Machine Learning Research, 18(50): 1-41, 2017. [Paper] [Preprint] [Code]
-
S. Haghiri, D. Ghoshdastidar, U. von Luxburg. Comparison based nearest neighbor search. AISTATS, 2017. [Paper] [Preprint]
-
D. Ghoshdastidar, A. Dukkipati. Consistency of Spectral Hypergraph Partitioning under Planted Partition Model. The Annals of Statistics, 45 (1): 289-315, 2017. [Paper] [Preprint]
-
A. Dukkipati, D. Ghoshdastidar, J. Krishnan. Mixture modelling with compact support distributions for unsupervised learning. IJCNN, 2016. [Paper]
-
D. Ghoshdastidar, A. P. Adsul, A. Dukkipati. Learning with Jensen-Tsallis kernels. IEEE Transactions on Neural Networks and Learning Systems, 27 (10), pp. 2108-2119, 2016. [Paper]
-
D. Ghoshdastidar, A. Dukkipati. A provable generalized tensor spectral method for uniform hypergraph partitioning. ICML, 2015. [Paper] [Video]
-
D. Ghoshdastidar, A. Dukkipati. Spectral clustering using multilinear SVD: Analysis, approximations and applications. AAAI, 2015. [Paper]
-
D. Ghoshdastidar, A. Dukkipati. Consistency of spectral partitioning of uniform hypergraphs under planted partition model. NIPS, 2014. [Paper]
-
D. Ghoshdastidar, A. Dukkipati, S. Bhatnagar. Newton based stochastic optimization using q-Gaussian smoothed functional algorithms. Automatica, 50(10): 2606-2614, 2014. [Paper] [Preprint]
-
D. Ghoshdastidar, A. Dukkipati, A. P. Adsul, A. S. Vijayan. Spectral clustering with Jensen-type kernels and their multi-point extensions. CVPR, 2014. [Paper] [Preprint]
-
D. Ghoshdastidar, A. Dukkipati, S. Bhatnagar. Smoothed functional algorithms for stochastic optimization using q-Gaussian distributions. ACM Transactions on Modeling and Computer Simulation, 24(3):Article 17, 2014. [Paper] [Preprint]
-
A. Dukkipati, G. Pandey, D. Ghoshdastidar, P. Koley, D. M. V. Satya Sriram. Generative maximum entropy learning for multiclass classification. ICDM, 2013. [Paper] [Preprint]
-
D. Ghoshdastidar, A. Dukkipati. On power law kernels, corresponding Reproducing Kernel Hilbert Space and applications. AAAI, 2013. [Paper]
-
D. Ghoshdastidar, A. Dukkipati, S. Bhatnagar. q-Gaussian based Smoothed Functional algorithms for stochastic optimization. ISIT, 2012. [Paper] [Preprint]
Doctoral dissertations
-
Pascal Mattia Esser. Theoretical Foundations for Exploiting Unlabelled Data in Machine Learning. Technical University of Munich, 2024. [PDF]
-
Leena Chennuru Vankadara. Towards a theory of learning under extreme non-identifiability: Through the lens of causal learning and kernel clustering. University of Tübingen, 2023. [PDF]
Workshop papers / Preprints
-
L. Gosch, M. Sabanayagam, D. Ghoshdastidar, S. Günnemann. Provable robustness of (graph) neural networks against data poisoning and backdoor attacks. Neurips 2024 Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers) [Preprint]
-
V. Kaufmann, P. M. Esser, B. Zhu, D. Ghoshdatidar. Self-supervised learning approaches to improve residential housing energy prediction accuracy. GNI Symposium & Expo on Artificial Intelligence for the Built World 2024.
-
O. Bouattour, O. Kanjilal, D. Ghoshdastidar. Active learning surrogates for enhanced reliability assessment of engineering systems. GNI Symposium & Expo on Artificial Intelligence for the Built World 2024.
-
M. Eppert, S. Mukherjee, D. Ghoshdastidar. Recovering imbalanced clusters via gradient based projection pursuit. LinStat 2024
-
M. Sabanayagam, P. Esser, D. Ghoshdastidar. New insights into graph convolutional networks using neural tangent kernels. MLG2022@ECMLPKDD [Preprint]
-
N. Ayday, D. Ghoshdastidar. Improvement on incremental spectral clustering. LWDA 2021.
-
V. Starlinger, C. de la Rua Lope and D. Ghoshdastidar. Machine Learning Benchmark to Assess the Environmental Impact of Cars. AAAI 2021 AI for Urban Mobility Workshop. [Paper] [Data/code]
-
D. Ghoshdastidar and U. von Luxburg. Do nonparametric two-sample tests work for small sample size? A study on random graphs. NIPS-2016 workshop on Adaptive and Scalable Nonparametric Methods in ML.
-
D. Ghoshdastidar, A. Dukkipati. Coloring random non-uniform bipartite hypergraphs. [Preprint]