Behnam Neyshabur

PhD Candidate

 
bneyshabur (at) ttic (dot) edu
Toyota Technological Institute at Chicago
6045 S. Kenwood Ave.
Chicago, IL 60637
 
Curriculum Vitae


I'm a PhD candidate at TTI-Chicago where I work with Nati Srebro. Starting fall 2017, I'll be a postdoctoral researcher working jointly with Sanjeev Arora at Institute for Advanced Study (IAS) in Princeton and Yann Lecun at NYU. I am interested in machine learning and optimization and my primary research is on optimization and generalization in deep learning.


Updates:
Publications (Google Scholar)

Exploring Generalization in Deep Learning,
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro.
Arxiv Preprint, 2017.
[arXiv:1706.08947]

Stabilizing GAN Training with Multiple Random Projections,
Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti.
Arxiv Preprint, 2017.
[arXiv:1705.07831] [Code]

Implicit Regularization in Matrix Factorization,
Suriya Gunasekar, Blake Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro.
Arxiv Preprint, 2017.
[arXiv:1705.09280]

Corralling a Band of Bandit Algorithms,
Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire.
The 30th Conference on Learning Theory (COLT), 2017.
[arXiv:1612.06246]

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations,
Behnam Neyshabur, Yuhuai Wu, Ruslan Salakhutdinov, Nathan Srebro.
Neural Information Processing Systems (NIPS) 29, 2016.
[arXiv:1605.07154]

Global Optimality of Local Search for Low Rank Matrix Recovery,
Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro.
Neural Information Processing Systems (NIPS) 29, 2016.
[arXiv:1605.07221]

Data-Dependent Path Normalization in Neural Networks,
Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro.
International Conference on Learning Representations (ICLR), 2016.
[arXiv:1511.06747]

Path-SGD: Path-Normalized Optimization in Deep Neural Networks,
Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro.
Neural Information Processing Systems (NIPS) 28, 2015.
[arXiv:1506.02617] [Code]

Norm-Based Capacity Control in Neural Networks,
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro.
The 28th Conference on Learning Theory (COLT), 2015.
[arXiv:1503.00036]

In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning,
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro.
International Conference on Learning Representations (ICLR) workshop track, 2015.
[arXiv:1412.6614] [ICLR poster]

On Symmetric and Asymmetric LSHs for Inner Product Search,
Behnam Neyshabur and Nathan Srebro.
32nd International Conference on Machine Learning (ICML), 2015.
[arXiv:1410.5518] [Implementation by Pushpendre Rastogi]

Joint Inference of Tissue-specific Networks with a Scale Free Topology,
Somaye Hashemifar, Behnam Neyshabur, Jinbo Xu.
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), 2015.

Clustering, Hamming Embedding, Generalized LSH and the Max Norm,
Behnam Neyshabur, Yury Makarychev, Nathan Srebro.
The 25th International Conference on Algorithmic Learning Theory (ALT), 2014.
[arXiv:1405.3167] [Slides]

Sparse Matrix Factorization: Simple rules for growing neural nets,
Behnam Neyshabur and Rina Panigrahy.
Arxiv Preprint, 2014.
[arXiv:1311.3315] [Slides]

The Power of Asymmetry in Binary Hashing,
Behnam Neyshabur, Payman Yadollahpour, Yury Makarychev, Ruslan Salakhutdinov, Nathan Srebro.
Neural Information Processing Systems (NIPS) 26, 2013.
[arXiv:1311.7662] [NIPS poster] [NatiĆ­s talk] [Slides] [Code]

NETAL: a new graph-based method for global alignment of protein-protein interaction networks,
Behnam Neyshabur, Ahmadreza Khadem, Somaye Hashemifar, Seyed Shahriar Arab.
Bioinformatics, 29(13): 1654-1662 (2013).
[link] [Supplementary Information] [Code]


Internships


Talks

  • The Geometry of Optimization and Generalization in Neural Networks: A Path-based Approach. Theory of Deep Learning Workshop at ICML, New York, 2016.
  • Optimization and Generalization in Multi-Layer Neural Networks. Facebook AI Research, New York, 2015.
  • Sparse Matrix Factorization: simple rules for growing deep networks. Microsoft Research, Silicon Valley, 2013.

Professional Activities
  • Conference reviewer for NIPS, ICML, COLT, ICLR, AAAI, AISTATS.
  • Journal reviewer for Neural Networks, IEEE Transactions on Image Processing, IEEE Transactions on Signal Processing

Graduate Teaching Assistantship

Other Interests
  • I'm a BIG fan of hiking/backpacking and in the last five years, I have visited more than 20 national parks in US. Some of my favorites NPs are Glacier, Yellowstone, Zion, Yosemite and Isle Royale.
  • I believe that communities can have a great role in our lives. That is why I currently served as the president of Persian Cultural Society of Chicago for five years.