Abbas Mehrabian

Artificial Intelligence · 2017–2018

A researcher in the Science corpus: 4 papers; trusts 8 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 17 citations into it; #30,562 of 35,345 by trust here, #17,776 by citations
• Scaling & Learning Theory — 8 citations into it; #206 of 428 by trust here, #218 by citations
• Statistical Learning Theory — 6 citations into it

Whom Abbas Mehrabian trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Matus Telgarsky
2. Peter L. Bartlett
3. Nadav Cohen

Who trusts Abbas Mehrabian overall

1. Behnam Neyshabur
2. Nimit Sharad Sohoni
3. Zhiwei Jia
4. Shiyong Lan
5. Max H. Farrell

Papers from Abbas Mehrabian's perspective

Ordered by how strongly the researchers Abbas Mehrabian trusts endorse each paper. Same corpus, a different order for every researcher.

1. On the Expressive Power of Deep Learning: A Tensor Analysis
2. Deep Learning
3. The Power of Depth for Feedforward Neural Networks
4. Benefits of Depth in Neural Networks
5. Approximation capabilities of multilayer feedforward networks
6. Error bounds for approximations with deep ReLU networks
7. Learnability and the Vapnik-Chervonenkis dimension
8. Matrix analysis
9. Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks
10. High-Dimensional Probability: An Introduction with Applications in Data Science

Their papers

• Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks (2017) — 548 citations
• Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes (2018) — 68 citations
• The total variation distance between high-dimensional Gaussians (2018) — 259 citations
• Nearly-tight VC-dimension bounds for piecewise linear neural networks (2017) — 190 citations