World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
39
Citations
12977
World Ranking
9504
National Ranking
154

Overview

Daniel Soudry is affiliated with the Technion - Israel Institute of Technology in Israel. Their work primarily falls within the field of Computer Science, with a substantial focus on Artificial Intelligence and related subfields.

Their research contributions span several subfields, including:

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Computational Mechanics

Within these subfields, the main topics covered by their publications include:

  • Advanced Neural Network Applications
  • Domain Adaptation and Few-Shot Learning
  • Stochastic Gradient Optimization Techniques
  • Adversarial Robustness in Machine Learning
  • Model Reduction and Neural Networks
  • Neural Networks and Applications
  • Machine Learning and Algorithms

Daniel Soudry's recent papers demonstrate ongoing engagement with neural network quantization, sparse training methods, and implicit bias in deep learning. Notable publications include:

  • Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming, 2020, arXiv (Cornell University)
  • Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks, 2021, arXiv (Cornell University)
  • Neural gradients are near-lognormal: improved quantized and sparse training, 2020, arXiv (Cornell University)
  • Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy, 2020, arXiv (Cornell University)
  • On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent, 2021, arXiv (Cornell University)

The majority of their publications have appeared in the venue arXiv (Cornell University), with 38 papers recorded there. Other publication venues include:

  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Semiconductor Science and Technology
  • Neural Computation

The researcher collaborates regularly with a group of co-authors, including:

  • Ron Banner
  • Nathan Srebro
  • Brian Chmiel
  • Itay Evron
  • Itay Hubara

Best Publications

  • Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

    Matthieu Courbariaux;Itay Hubara;Daniel Soudry;Ran El-Yaniv

  • Quantized neural networks: training neural networks with low precision weights and activations

    Itay Hubara;Matthieu Courbariaux;Daniel Soudry;Ran El-Yaniv

  • Binarized Neural Networks

    Itay Hubara;Matthieu Courbariaux;Daniel Soudry;Ran El-Yaniv

  • Simultaneous Denoising, Deconvolution, and Demixing of Calcium Imaging Data

    Eftychios A. Pnevmatikakis;Daniel Soudry;Yuanjun Gao;Timothy A. Machado

  • Train longer, generalize better: closing the generalization gap in large batch training of neural networks

    Elad Hoffer;Itay Hubara;Daniel Soudry

  • The implicit bias of gradient descent on separable data

    Daniel Soudry;Elad Hoffer;Mor Shpigel Nacson;Suriya Gunasekar

  • Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training

    Daniel Soudry;Dotan Di Castro;Asaf Gal;Avinoam Kolodny

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

    Ron Banner;Yury Nahshan;Daniel Soudry

  • No bad local minima: Data independent training error guarantees for multilayer neural networks

    Daniel Soudry;Yair Carmon

  • Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights

    Daniel Soudry;Itay Hubara;Ron Meir

  • Scalable methods for 8-bit training of neural networks

    Ron Banner;Itay Hubara;Elad Hoffer;Daniel Soudry

  • Implicit Bias of Gradient Descent on Linear Convolutional Networks

    Suriya Gunasekar;Jason D. Lee;Daniel Soudry;Nathan Srebro

  • Characterizing Implicit Bias in Terms of Optimization Geometry

    Suriya Gunasekar;Jason D. Lee;Daniel Soudry;Nathan Srebro

  • Extracting grid cell characteristics from place cell inputs using non-negative principal component analysis

    Yedidyah Dordek;Daniel Soudry;Ron Meir;Dori Derdikman

  • Augment Your Batch: Improving Generalization Through Instance Repetition

    Elad Hoffer;Tal Ben-Nun;Itay Hubara;Niv Giladi

  • Post-training 4-bit quantization of convolution networks for rapid-deployment

    Ron Banner;Yury Nahshan;Elad Hoffer;Daniel Soudry

  • Norm matters: efficient and accurate normalization schemes in deep networks

    Elad Hoffer;Ron Banner;Itay Golan;Daniel Soudry

  • Kernel and Rich Regimes in Overparametrized Models

    Blake E. Woodworth;Suriya Gunasekar;Jason D. Lee;Edward Moroshko

  • Task Agnostic Continual Learning Using Online Variational Bayes

    Chen Zeno;Itay Golan;Elad Hoffer;Daniel Soudry

  • The Knowledge Within: Methods for Data-Free Model Compression

    Matan Haroush;Itay Hubara;Elad Hoffer;Daniel Soudry

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

    Greg Ongie;Rebecca Willett;Daniel Soudry;Nathan Srebro

  • The Implicit Bias of Gradient Descent on Separable Data

    Daniel Soudry;Elad Hoffer;Mor Shpigel Nacson;Nathan Srebro

  • The Implicit Bias of Gradient Descent on Separable Data

    Daniel Soudry;Elad Hoffer;Nathan Srebro

Frequent Co-Authors

Nathan Srebro
Nathan Srebro Toyota Technological Institute at Chicago
Ron Meir
Ron Meir Technion – Israel Institute of Technology
Jason D. Lee
Jason D. Lee Princeton University
Liam Paninski
Liam Paninski Columbia University
Shahar Kvatinsky
Shahar Kvatinsky Technion – Israel Institute of Technology
Ran El-Yaniv
Ran El-Yaniv Technion – Israel Institute of Technology
Rafael Yuste
Rafael Yuste Columbia University
Yoshua Bengio
Yoshua Bengio University of Montreal
Misha B. Ahrens
Misha B. Ahrens Howard Hughes Medical Institute

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Studying Computer Science in the USA opens doors to many online degree programs and career opportunities. For those interested in engineering, consider exploring online electrical engineering career outcomes to understand potential job prospects and industries that hire graduates with technical expertise.

Not everyone wants to commit to years of study. If you’re seeking a quick credential, check out easy licenses and certifications to get for a faster route to high-paying tech roles. These flexible options can provide specialized skills that are valued in today's job market.

Time-sensitive students might also look into the shortest master degree programs available online. Earning an advanced degree in less time can accelerate your entry into competitive fields.

Lastly, stay informed about the most in demand masters degrees so you can align your education with booming industries like data science, artificial intelligence, and software development.

Best Scientists Citing Daniel Soudry

Trending Scientists

Recently Published Articles