Search Results for author: Supratim Shit

Found 4 papers, 2 papers with code

Efficient NTK using Dimensionality Reduction

no code implementations10 Oct 2022 Nir Ailon, Supratim Shit

Recently, neural tangent kernel (NTK) has been used to explain the dynamics of learning parameters of neural networks, at the large width limit.

Dimensionality Reduction

Online Coresets for Clustering with Bregman Divergences

no code implementations11 Dec 2020 Rachit Chhaya, Jayesh Choudhari, Anirban Dasgupta, Supratim Shit

Our first algorithm gives online coresets of size $\tilde{O}(\mbox{poly}(k, d,\epsilon,\mu))$ for $k$-clusterings according to any $\mu$-similar Bregman divergence.

Clustering

On Coresets For Regularized Regression

1 code implementation ICML 2020 Rachit Chhaya, Anirban Dasgupta, Supratim Shit

We propose a modified version of the lasso problem and obtain for it a coreset of size smaller than the least square regression.

regression

Streaming Coresets for Symmetric Tensor Factorization

1 code implementation ICML 2020 Rachit Chhaya, Jayesh Choudhari, Anirban Dasgupta, Supratim Shit

Factorizing tensors has recently become an important optimization module in a number of machine learning pipelines, especially in latent variable models.

Cannot find the paper you are looking for? You can Submit a new open access paper.