bneyshabur (at) ttic (dot) edu
Toyota Technological Institute at Chicago
6045 S. Kenwood Ave.
Chicago, IL 60637
I'm interested in following research areas:
I'm a PhD candidate at TTI-Chicago,
a philanthropically endowed academic computer science institute located on the
University of Chicago campus. My advisor is
- Machine Learning, Learning Theory, Optimization
- Deep Learning, Neural Networks
- Metric Learning, Nearest Neighbor, Binary Hashing
- Compressed sensing, Matrix Factorization, Collaborative filtering
- Computational Biology
- May, 2016: New paper on path-normalized optimization of RNNs with ReLU activations.
- May, 2016: New paper showing that local minima of some rank-constraint problems are in fact global minima.
- May, 2016: I will be giving a talk at Theory of Deep Learning Workshop ICML 2016.
- Apr, 2016: This summer, I will be an intern at Microsoft Research New York City.
- Feb, 2016: Our paper on Data-Dependent Path Normalization in Neural Networks is accepted to ICLR.
- Oct, 2015: I gave a talk at Facebook AI Research on optimization and generalization in deep learning.
- Sep, 2015: Our paper on path-normalized optimization in deep learning is accepted to NIPS.
Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations,
Technical report, arXiv:1605.07154, 2016.
Global Optimality of Local Search for Low Rank Matrix Recovery,
Technical report, arXiv:1605.07221, 2016.
Data-Dependent Path Normalization in Neural Networks,
International Conference on Learning Representations (ICLR), 2016 (to appear).
Path-SGD: Path-Normalized Optimization in Deep Neural Networks,
Neural Information Processing Systems (NIPS) 28, 2015.
Joint Inference of Tissue-specific Networks with a Scale Free Topology,
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), 2015.
Norm-Based Capacity Control in Neural Networks,
The 28th Conference on Learning Theory (COLT), 2015.
In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning,
International Conference on Learning Representations (ICLR) workshop track, 2015.
On Symmetric and Asymmetric LSHs for Inner Product Search,
Behnam Neyshabur and Nathan Srebro.
32nd International Conference on Machine Learning (ICML), 2015.
[Implementation by Pushpendre Rastogi]
Clustering, Hamming Embedding, Generalized LSH and the Max Norm,
The 25th International Conference on Algorithmic Learning Theory (ALT), 2014.
Sparse Matrix Factorization: Simple rules for growing neural nets,
Behnam Neyshabur and Rina Panigrahy.
Technical report, arXiv:1311.3315, 2014.
The Power of Asymmetry in Binary Hashing,
Neural Information Processing Systems (NIPS) 26, 2013.
NETAL: a new graph-based method for global alignment of protein-protein interaction networks,
Seyed Shahriar Arab.
Bioinformatics, 29(13): 1654-1662 (2013).
- Research Intern (Aug 2013 - Nov 2013), Microsoft Research
- Research Intern (Jun 2016 - Sep 2016), Microsoft Research
- Conference reviewer for NIPS, COLT, ICML, ICLR, AAAI.
- Journal reviewer for Computational Intelligence and Neuroscience, IEEE Transactions on Signal Processing
Graduate Teaching Assistantship
- Convex Optimization, TTIC and University of Chicago, Autumn 2015.
- Statistical and Computational Learning Theory, TTIC and University of Chicago, Spring 2015.
- Algorithms, TTIC and University of Chicago, Winter 2013.
- Statistical and Computational Learning Theory, TTIC and University of Chicago, Autumn 2012.
- Algorithms, University of Chicago, Autumn 2011.
- Game Theory, Sharif University of Technology, Autumn 2010.
I love hiking. Although all amazing hiking trails are far from Chicago, I did manage to visit several National Parks in US and every one of them was indeed a unique experience.