no code implementations • 24 Feb 2024 • Saptarshi Chakraborty, Peter L. Bartlett
To bridge the gap between the theory and practice of WAEs, in this paper, we show that WAEs can learn the data distributions when the network architectures are properly chosen.
no code implementations • 28 Jan 2024 • Saptarshi Chakraborty, Peter L. Bartlett
In this paper, we attempt to bridge the gap between the theory and practice of GANs and their bidirectional variant, Bi-directional GANs (BiGANs), by deriving statistical guarantees on the estimated densities in terms of the intrinsic dimension of the data and the latent space.
1 code implementation • 22 Jun 2022 • Adithya Vellal, Saptarshi Chakraborty, Jason Xu
Recent progress in center-based clustering algorithms combats poor local minima by implicit annealing, using a family of generalized means.
no code implementations • 6 Jan 2022 • Saptarshi Chakraborty, Debolina Paul, Swagatam Das
The problem of linear predictions has been extensively studied for the past century under pretty generalized frameworks.
1 code implementation • NeurIPS 2021 • Debolina Paul, Saptarshi Chakraborty, Swagatam Das, Jason Xu
Recent advances in center-based clustering continue to improve upon the drawbacks of Lloyd's celebrated $k$-means algorithm over $60$ years after its introduction.
no code implementations • 5 Feb 2021 • Debolina Paul, Saptarshi Chakraborty, Swagatam Das
Principal Component Analysis (PCA) is a fundamental tool for data visualization, denoising, and dimensionality reduction.
1 code implementation • 20 Dec 2020 • Saptarshi Chakraborty, Debolina Paul, Swagatam Das
Mean shift is a simple interactive procedure that gradually shifts data points towards the mode which denotes the highest density of data points in the region.
no code implementations • 12 Nov 2020 • Debolina Paul, Saptarshi Chakraborty, Swagatam Das, Jason Xu
We show the method implicitly performs annealing in kernel feature space while retaining efficient, closed-form updates, and we rigorously characterize its convergence properties both from computational and statistical points of view.
no code implementations • 17 Aug 2020 • Debolina Paul, Saptarshi Chakraborty, Didong Li, David Dunson
In a rich variety of real data clustering applications, PEA is shown to do as well as k-means for simple datasets, while dramatically improving performance in more complex settings.
1 code implementation • 10 Jan 2020 • Saptarshi Chakraborty, Debolina Paul, Swagatam Das, Jason Xu
Despite its well-known shortcomings, $k$-means remains one of the most widely used approaches to data clustering.
no code implementations • 24 Mar 2019 • Saptarshi Chakraborty, Swagatam Das
We propose the Lasso Weighted $k$-means ($LW$-$k$-means) algorithm as a simple yet efficient sparse clustering procedure for high-dimensional data where the number of features ($p$) can be much larger compared to the number of observations ($n$).
no code implementations • 9 May 2014 • Saptarshi Chakraborty, Dhrubajyoti Das
The main aim is to provide a simple path for the future development of novel and more secured face liveness detection approach.