4 citations · 14 across the 40 of their papers we have counts for
6 papers · 1 filter
Approximation Theory for Neural Networks: Old and New
Soumendu Sundar Mukherjee, Himasish Talukdar
Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function,…
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
Akhil Jalan, Yassir Jedra, Arya Mazumdar +2
We study transfer learning for matrix completion in a Missing Not-at-Random (MNAR) setting that is motivated by biological problems. The target matrix has entire rows and colum…
Transfer Learning for Latent Variable Network Models
Akhil Jalan, Arya Mazumdar, Soumendu Sundar Mukherjee +1
We study transfer learning for estimation in latent variable network models. In our setting, the conditional edge probability matrices given the latent variables are represented by…
Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing
Hong T. M. Chu, Subhro Ghosh, Xiaoyu Dong +2
The phenomenon of implicit bias has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails…
Wasserstein Projection Pursuit of Non-Gaussian Signals
Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar
We consider the general dimensionality reduction problem of locating in a high-dimensional data cloud, a -dimensional non-Gaussian subspace of interesting features. We use a pro…
Morphological Network: How Far Can We Go with Morphological Neurons?
Ranjan Mondal, Sanchayan Santra, Soumendu Sundar Mukherjee +1
Morphological neurons, that is morphological operators such as dilation and erosion with learnable structuring elements, have intrigued researchers for quite some time because of t…