6 citations · 16 across the 10 of their papers we have counts for
5 papers · 1 filter
Implicit Regularization for Group Sparsity
Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde +1
We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network…
Autoencoders Learn Generative Linear Models
Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde
We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on thre…
On Learning Sparsely Used Dictionaries from Incomplete Samples
Thanh V. Nguyen, Akshay Soni, Chinmay Hegde
Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such a…
Provably Accurate Double-Sparse Coding
Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde
Sparse coding is a crucial subroutine in algorithms for various signal processing, deep learning, and other machine learning applications. The central goal is to learn an overcompl…
A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
Aditya Balu, Thanh V. Nguyen, Apurva Kokate +2
We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image,…