1 code implementation • 29 Jan 2023 • Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong
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.
1 code implementation • 29 Sep 2021 • Jiangyuan Li, Mohammadreza Armandpour
In this paper, we develop a deep learning approach based on encoder-decoder structure.
1 code implementation • NeurIPS 2021 • Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong
In this paper, we study the implicit bias of gradient descent for sparse regression.