Zobrazeno 1 - 10
of 109
pro vyhledávání: '"Asnani, Himanshu"'
Recently a class of generalized information measures was defined on sets of items parametrized by submodular functions. In this paper, we propose and study various notions of independence between sets with respect to such information measures, and co
Externí odkaz:
http://arxiv.org/abs/2108.03154
Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as `dropout' events. Recently, Regularized Auto-Encoder (RAE) based deep neural network
Externí odkaz:
http://arxiv.org/abs/2107.07709
Autor:
Kaushal, Vishal, Kothawade, Suraj, Ramakrishnan, Ganesh, Bilmes, Jeff, Asnani, Himanshu, Iyer, Rishabh
We study submodular information measures as a rich framework for generic, query-focused, privacy sensitive, and update summarization tasks. While past work generally treats these problems differently ({\em e.g.}, different models are often used for g
Externí odkaz:
http://arxiv.org/abs/2010.05631
Information-theoretic quantities like entropy and mutual information have found numerous uses in machine learning. It is well known that there is a strong connection between these entropic quantities and submodularity since entropy over a set of rand
Externí odkaz:
http://arxiv.org/abs/2006.15412
Regularized Auto-Encoders (RAEs) form a rich class of neural generative models. They effectively model the joint-distribution between the data and the latent space using an Encoder-Decoder combination, with regularization imposed in terms of a prior
Externí odkaz:
http://arxiv.org/abs/2006.05838
Autor:
Mondal, Arnab Kumar, Bhattacharya, Arnab, Mukherjee, Sudipto, AP, Prathosh, Kannan, Sreeram, Asnani, Himanshu
Estimation of information theoretic quantities such as mutual information and its conditional variant has drawn interest in recent times owing to their multifaceted applications. Newly proposed neural estimators for these quantities have overcome sev
Externí odkaz:
http://arxiv.org/abs/2005.08226
Autor:
Mondal, Arnab Kumar, Chowdhury, Sankalan Pal, Jayendran, Aravind, Singla, Parag, Asnani, Himanshu, AP, Prathosh
The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse. Auto-Encoders (AE) with regularized latent space provide an a
Externí odkaz:
http://arxiv.org/abs/1912.04564
Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians for commu
Externí odkaz:
http://arxiv.org/abs/1911.03038
Conditional Mutual Information (CMI) is a measure of conditional dependence between random variables X and Y, given another random variable Z. It can be used to quantify conditional dependence among variables in many data-driven inference problems su
Externí odkaz:
http://arxiv.org/abs/1906.01824
Standard decoding approaches rely on model-based channel estimation methods to compensate for varying channel effects, which degrade in performance whenever there is a model mismatch. Recently proposed Deep learning based neural decoders address this
Externí odkaz:
http://arxiv.org/abs/1903.02268