PM

Poorya Mianjy

cs.LGstat.MLcs.AIcond-mat.dis-nncs.CCcs.CR

On Valency

published · living versions

Understanding Deep Neural Networks with Rectified Linear Units

with Raman Arora, Amitabh Basu, Anirbit Mukherjee

1 version

W_6r3j4kw4v1 · current

Preprints & journals

8 papers in the corpus · 2016–2022

Adversarial Robustness is at Odds with Lazy Training

Yunjuan Wang, Enayat Ullah, Poorya Mianjy et al.

3 citations

2207.00411v22022arXiv

On Convergence and Generalization of Dropout Training

Poorya Mianjy, Raman Arora

15 citations

2010.12711v12020In Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2020

Dropout: Explicit Forms and Capacity Control

Raman Arora, Peter Bartlett, Poorya Mianjy et al.

13 citations

2003.03397v12020arXiv

On Dropout and Nuclear Norm Regularization

Poorya Mianjy, Raman Arora

16 citations

1905.11887v12019Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4575-4584, 2019

Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features

Enayat Ullah, Poorya Mianjy, Teodor V. Marinov et al.

1 citation

1808.00934v22018arXiv

On the Implicit Bias of Dropout

Poorya Mianjy, Raman Arora, Rene Vidal

39 citations

1806.09777v12018arXiv

Stochastic Approximation for Canonical Correlation Analysis

Raman Arora, Teodor V. Marinov, Poorya Mianjy et al.

20 citations

1702.06818v22017arXiv

Understanding Deep Neural Networks with Rectified Linear Units

Raman Arora, Amitabh Basu, Poorya Mianjy et al.

372 citations

1611.01491v62016ICLR 2028

Career total: 15 works. 8 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.