Publications & Preprints

(2024) A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data. S. Chakraborty and P. Bartlett. arXiv

(2024) On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension. S. Chakraborty and P. Bartlett. arXiv

(2024) A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data. S. Chakraborty and P. Bartlett. International Conference on Learning Representations (ICLR). Paper   arXiv   Github.

(2023) Biconvex Clustering. S. Chakraborty and J. Xu. Journal of Computational and Graphical Statistics. Paper   arXiv   Github.

(2023) Robust Principal Component Analysis: A Median of Means Approach. D. Paul, S. Chakraborty and S. Das. IEEE Transactions on Neural Networks and Learning Systems. Paper

(2023) Clustering High-dimensional Data with Ordered Weighted L1 Regularization. C. Chakraborty, S. Paul, S. Chakraborty, and S. Das. International Conference on Artificial Intelligence and Statistics (AISTATS). Paper   Github.

(2022) Bregman Power k-Means for Clustering Exponential Family Data. A. Vellal, S. Chakraborty and J. Xu. International Conference on Machine Learning (ICML). Paper   Github.

(2022) Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach. D. Paul, S. Chakraborty, S. Das and J. Xu. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI). Paper

(2022) A Consistent Entropy-Regularized Weighted k-Means Clustering Algorithm. D. Paul, S. Chakraborty, and S. Das. IEEE Transactions on Cybernetics. Paper

(2021) Uniform Concentration Bounds toward a Unified Framework for Robust Clustering. D. Paul, S. Chakraborty, S. Das and J. Xu. Neural Information Processing Systems (NeurIPS). Paper

(2021) On Uniform Concentration Bounds for Bi-clustering by using the Vapnik-Chervonenkis Theory. S. Chakraborty, and S. Das. Statistics and Probability Letters. Paper

(2021) Automated Clustering of High-dimensional Data with a Feature Weighted Mean-shift Algorithm. S. Chakraborty, D. Paul and S. Das. AAAI Conference on Artificial Intelligence (AAAI). Paper   arXiv   Github.

(2021) On the Uniform Concentration Bounds and Large Sample Properties of Clustering with Bregman Divergences. D. Paul , S. Chakraborty and S. Das. Stat. Paper.

(2021) Detecting Meaningful Clusters from High-dimensional Data: A Strongly Consistent Sparse Center-based Clustering Approach. S. Chakraborty and S. Das. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Paper   Github.

(2020) Entropy Weighted Power k-Means Clustering. S. Chakraborty, D. Paul, S. Das and J. Xu. International Conference on Artificial Intelligence and Statistics (AISTATS). Paper   arXiv.

(2020) Hierarchical Clustering with Optimal Transport Statistics and Probability Letters. S. Chakraborty, D. Paul and S. Das. Statistics and Probability Letters. Paper.

(2019) On the strong consistency of feature-weighted k-means clustering in a nearmetric space. S. Chakraborty and S. Das. Stat. Paper.

(2019) On the non-convergence of differential evolution: some generalized adversarial conditions and a remedy. D. Paul, S. Chakraborty, S. Das and I. Zelinka. Genetic and Evolutionary Computation Conference Companion (GECCO). Paper.

(2018) Simultaneous variable weighting and determining the number of clusters—A weighted Gaussian means algorithm. S. Chakraborty and S. Das. Statistics and Probability Letters. Paper   Github.

(2017) k-Means clustering with a new divergence-based distance metric: Convergence and performance analysis. S. Chakraborty and S. Das. Pattern Recognition Letters. Paper   Github.