Publications & Preprints
(2026) Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data.
Saptarshi Chakraborty, Quentin Berthet and Peter Bartlett.
arXiv
(2026) Efficient Logistic Regression with Mixture of Sigmoids.
Federico Di Gennaro, Saptarshi Chakraborty, Nikita Zhivotovskiy. International Conference on Artificial Intelligence and Statistics (AISTATS).
arXiv
(2026) A New Framework for Convex Clustering in Kernel Spaces: Finite Sample Bounds, Consistency and Performance Insights.
Shubhayan Pan, Saptarshi Chakraborty, Debolina Paul, Kushal Bose, and Swagatam Das. International Joint Conference on Artificial Intelligence (IJCAI-ECAI). Accepted.
arXiv
(2026) Convex Clustering Redefined: Robust Learning With the Median of Means Estimator.
Koustav Chowdhury, Bibhabasu Mandal, Sourav De, Sagar Ghosh, Swagatam Das, Debolina Paul, Saptarshi Chakraborty. AAAI Conference on Artificial Intelligence (AAAI).
Paper arXiv Talk
(2025) On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension.
Saptarshi Chakraborty and Peter Bartlett. Journal of Machine Learning Research (JMLR).
arXiv Paper
(2025) Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs.
Saptarshi Chakraborty and Peter Bartlett. International Conference on Artificial Intelligence and Statistics (AISTATS).
Paper
(2025) Minimax Rates for Distribution Estimation on Low-dimensional Spaces.
Saptarshi Chakraborty. Transactions on Machine Learning Research (TMLR).
Paper
(2024) A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data.
Saptarshi Chakraborty and Peter Bartlett.
arXiv
(2024) A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data.
Saptarshi Chakraborty and Peter Bartlett.
arXiv
(2024) A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data.
Saptarshi Chakraborty and Peter Bartlett. International Conference on Learning Representations (ICLR).
Paper arXiv Github
(2023) Biconvex Clustering.
Saptarshi Chakraborty and Jason Xu. Journal of Computational and Graphical Statistics (JCGS).
Paper arXiv Github
(2023) Robust Principal Component Analysis: A Median of Means Approach.
Debolina Paul, Saptarshi Chakraborty and Swagatam Das. IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS).
Paper
(2023) Clustering High-dimensional Data with Ordered Weighted L1 Regularization.
Chandramauli Chakraborty, Sayan Paul, Saptarshi Chakraborty, and Swagatam Das. International Conference on Artificial Intelligence and Statistics (AISTATS).
Paper Github
(2022) Bregman Power k-Means for Clustering Exponential Family Data.
Adithya Vellal, Saptarshi Chakraborty and Jason Xu. International Conference on Machine Learning (ICML). Spotlight.
Paper Github
(2022) Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach.
Debolina Paul, Saptarshi Chakraborty, Swagatam Das and Jason Xu. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI).
Paper
(2022) A Consistent Entropy-Regularized Weighted k-Means Clustering Algorithm.
Debolina Paul, Saptarshi Chakraborty, and Swagatam Das. IEEE Transactions on Cybernetics (IEEE TCYB).
Paper
(2021) Uniform Concentration Bounds toward a Unified Framework for Robust Clustering.
Debolina Paul, Saptarshi Chakraborty, Swagatam Das and Jason Xu. Neural Information Processing Systems (NeurIPS). Spotlight.
Paper
(2021) On Uniform Concentration Bounds for Bi-clustering using VC Theory.
Saptarshi Chakraborty and Swagatam Das. Statistics and Probability Letters.
Paper
(2021) $t$-Entropy: A New Measure of Uncertainty with Some Applications.
Saptarshi Chakraborty, Debolina Paul and Swagatam Das. IEEE International Symposium on Information Theory (ISIT).
Paper arXiv Github
(2021) Automated Clustering of High-dimensional Data with a Feature Weighted Mean-shift Algorithm.
Saptarshi Chakraborty, Debolina Paul and Swagatam 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.
Debolina Paul, Saptarshi Chakraborty and Swagatam Das. Stat.
Paper
(2021) Detecting Meaningful Clusters from High-dimensional Data: A Strongly Consistent Sparse Center-based Clustering Approach.
Saptarshi Chakraborty and Swagatam Das. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI).
Paper Github
(2020) Entropy Weighted Power k-Means Clustering.
Saptarshi Chakraborty, Debolina Paul, Swagatam Das and Jason Xu. International Conference on Artificial Intelligence and Statistics (AISTATS).
Paper arXiv
(2020) Hierarchical Clustering with Optimal Transport.
Saptarshi Chakraborty, Debolina Paul and Swagatam Das. Statistics and Probability Letters.
Paper
(2019) On the Strong Consistency of Feature-weighted k-means in Near-metric Spaces.
Saptarshi Chakraborty and Swagatam Das. Stat.
Paper
(2019) On the Non-convergence of Differential Evolution: Adversarial Conditions and a Remedy.
Debolina Paul, Saptarshi Chakraborty, Swagatam Das and Ivan Zelinka. Genetic and Evolutionary Computation Conference Companion (GECCO Companion).
Paper
(2018) Simultaneous Variable Weighting and Determining the Number of Clusters — A Weighted Gaussian Means Algorithm.
Saptarshi Chakraborty and Swagatam Das. Statistics and Probability Letters.
Paper Github
(2017) k-Means Clustering with a New Divergence-based Distance Metric: Convergence and Performance Analysis.
Saptarshi Chakraborty and Swagatam Das. Pattern Recognition Letters.
Paper Github