Daniel Soudry

Assistant Professor

Department of Electrical Engineering, Technion

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

I am especially interested in all aspects of neural networks and deep learning

Papers72 papers

Sort

By YearBy Citation

Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner,Daniel Soudry

Cited by1Bibtex

At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks

Niv Giladi, Mor Shpigel Nacson,Elad Hoffer,Daniel Soudry

ICLR, (2020)

Cited by2EIBibtex

Kernel and Rich Regimes in Overparametrized Models

Woodworth Blake,Gunasekar Suriya,Lee Jason D., Moroshko Edward,Savarese Pedro, Golan Itay,Soudry Daniel,Srebro Nathan

COLT, pp.3635-3673, (2020)

Cited by36EIBibtex

A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Greg Ongie,Rebecca Willett,Daniel Soudry,Nathan Srebro

ICLR, (2020)

Cited by15EIBibtex

Augment Your Batch: Improving Generalization Through Instance Repetition

Elad Hoffer,Tal Ben-Nun,Itay Hubara,Niv Giladi,Torsten Hoefler,Daniel Soudry

CVPR, pp.8126-8135, (2020)

EIBibtex

Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

Chen Zeno, Itay Golan, Elad Hoffer,Daniel Soudry

Bibtex

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

Edward Moroshko,Suriya Gunasekar,Blake Woodworth,Jason D. Lee,Nathan Srebro,Daniel Soudry

NeurIPS 2020, (2020)

Cited by2Bibtex

Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization

Yaniv Blumenfeld, Dar Gilboa,Daniel Soudry

ICML, pp.960-969, (2020)

Cited by1EIBibtex

Neural gradients are lognormally distributed: understanding sparse and quantized training

Chmiel Brian, Ben-Uri Liad,Shkolnik Moran,Hoffer Elad, Banner Ron,Soudry Daniel

Bibtex

Kernel and Deep Regimes in Overparametrized Models

Blake E. Woodworth,Suriya Gunasekar,Jason Lee,Daniel Soudry,Nathan Srebro

CoRR, (2019)

EIBibtex

The Global Optimization Geometry of Shallow Linear Neural Networks

Zhihui Zhu,Daniel Soudry,Yonina C. Eldar,Michael B. Wakin

Journal of Mathematical Imaging and Vision, no. 3 (2019): 279-292

Cited by12EIBibtex

Convergence of Gradient Descent on Separable Data

Mor Shpigel Nacson,Jason D. Lee,Suriya Gunasekar,Pedro H. P. Savarese,Nathan Srebro,Daniel Soudry

Bibtex

How do infinite width bounded norm networks look in function space

Pedro Savarese, Itay Evron,Daniel Soudry,Nathan Srebro

COLT, (2019): 2667-2690

Cited by34EIBibtex

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models

Mor Shpigel Nacson,Suriya Gunasekar,Jason D. Lee,Nathan Srebro,Daniel Soudry

International Conference on Machine Learning, (2019): 4683-4692

Cited by13EIBibtex

MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks

Toledo Tzofnat Greenberg, Perach Ben,Soudry Daniel,Kvatinsky Shahar

Cited by1Bibtex

Is Feature Diversity Necessary in Neural Network Initialization

Blumenfeld Yaniv, Gilboda Dar,Soudry Daniel

Bibtex

The Knowledge Within: Methods for Data-Free Model Compression

Haroush Matan,Hubara Itay,Hoffer Elad,Soudry Daniel

CVPR, pp.8491-8499, (2019)

Cited by9EIBibtex

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency

Hoffer Elad, Weinstein Berry,Hubara Itay,Ben-Nun Tal,Hoefler Torsten,Soudry Daniel

Cited by3Bibtex

A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off

Yaniv Blumenfeld, Dar Gilboa,Daniel Soudry

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 7036-7046

Cited by6EIBibtex

Post training 4-bit quantization of convolutional networks for rapid-deployment

Ron Banner, Yury Nahshan,Daniel Soudry

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 7948-7956

Cited by33EIBibtex

View All

Base Info Papers Patents Projects

Daniel SoudryBinding

Papers72 papers

Daniel Soudry