Daniel Soudry

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 101

Top Venues

CoRR

NeurIPS

ICLR

ICML

Publications

Daniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry, Paul Hand
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical Model. CoRR (2024)
Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators. CoRR (2024)
Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes. CoRR (2024)
Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson, Alon Brutzkus, Nathan Srebro, Daniel Soudry
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers. CoRR (2024)
Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators. ICLR (2024)
Daniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry, Paul Hand
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical Model. ICLR (2024)
Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. CoRR (2023)
Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer, Kfir Yehuda Levy, Daniel Soudry
DropCompute: simple and more robust distributed synchronous training via compute variance reduction. CoRR (2023)
Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. ICML (2023)
Itay Evron, Ophir Onn, Tamar Weiss Orzech, Hai Azeroual, Daniel Soudry
The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study. AISTATS (2023)
Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer, Kfir Y. Levy, Daniel Soudry
DropCompute: simple and more robust distributed synchronous training via compute variance reduction. NeurIPS (2023)
Itay Evron, Ophir Onn, Tamar Weiss Orzech, Hai Azeroual, Daniel Soudry
The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study. CoRR (2023)
Mor Shpigel Nacson, Rotem Mulayoff, Greg Ongie, Tomer Michaeli, Daniel Soudry
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks. CoRR (2023)
Mor Shpigel Nacson, Rotem Mulayoff, Greg Ongie, Tomer Michaeli, Daniel Soudry
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks. ICLR (2023)
Ev Zisselman, Itai Lavie, Daniel Soudry, Aviv Tamar
Explore to Generalize in Zero-Shot RL. NeurIPS (2023)
Ev Zisselman, Itai Lavie, Daniel Soudry, Aviv Tamar
Explore to Generalize in Zero-Shot RL. CoRR (2023)
Brian Chmiel, Ron Banner, Elad Hoffer, Hilla Ben-Yaacov, Daniel Soudry
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats. ICLR (2023)
Chen Zeno, Greg Ongie, Yaniv Blumenfeld, Nir Weinberger, Daniel Soudry
How do Minimum-Norm Shallow Denoisers Look in Function Space? CoRR (2023)
Itay Evron, Edward Moroshko, Gon Buzaglo, Maroun Khriesh, Badea Marjieh, Nathan Srebro, Daniel Soudry
Continual Learning in Linear Classification on Separable Data. ICML (2023)
Itay Evron, Edward Moroshko, Gon Buzaglo, Maroun Khriesh, Badea Marjieh, Nathan Srebro, Daniel Soudry
Continual Learning in Linear Classification on Separable Data. CoRR (2023)
Hagay Michaeli, Tomer Michaeli, Daniel Soudry
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations. CVPR (2023)
Hagay Michaeli, Tomer Michaeli, Daniel Soudry
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations. CoRR (2023)
Brian Chmiel, Itay Hubara, Ron Banner, Daniel Soudry
Minimum Variance Unbiased N: M Sparsity for the Neural Gradients. ICLR (2023)
Chen Zeno, Greg Ongie, Yaniv Blumenfeld, Nir Weinberger, Daniel Soudry
How do Minimum-Norm Shallow Denoisers Look in Function Space? NeurIPS (2023)
Mor Shpigel Nacson, Kavya Ravichandran, Nathan Srebro, Daniel Soudry
Implicit Bias of the Step Size in Linear Diagonal Neural Networks. ICML (2022)
Brian Chmiel, Itay Hubara, Ron Banner, Daniel Soudry
Optimal Fine-Grained N: M sparsity for Activations and Neural Gradients. CoRR (2022)
Aviv Tamar, Daniel Soudry, Ev Zisselman
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability. AAAI (2022)
Itay Evron, Edward Moroshko, Rachel Ward, Nathan Srebro, Daniel Soudry
How catastrophic can catastrophic forgetting be in linear regression? COLT (2022)
Matan Haroush, Tzviel Frostig, Ruth Heller, Daniel Soudry
A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks. ICLR (2022)
Itay Evron, Edward Moroshko, Rachel Ward, Nati Srebro, Daniel Soudry
How catastrophic can catastrophic forgetting be in linear regression? CoRR (2022)
Niv Giladi, Zvika Ben-Haim, Sella Nevo, Yossi Matias, Daniel Soudry
Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling. CoRR (2021)
Aviv Tamar, Daniel Soudry, Ev Zisselman
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability. CoRR (2021)
Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
Task-Agnostic Continual Learning Using Online Variational Bayes With Fixed-Point Updates. Neural Comput. 33 (11) (2021)
Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, Daniel Soudry
Accurate Post Training Quantization With Small Calibration Sets. ICML (2021)
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake E. Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent. CoRR (2021)
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake E. Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent. ICML (2021)
Matan Haroush, Tzivel Frostig, Ruth Heller, Daniel Soudry
Statistical Testing for Efficient Out of Distribution Detection in Deep Neural Networks. CoRR (2021)
Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry
Neural gradients are near-lognormal: improved quantized and sparse training. ICLR (2021)
Itay Hubara, Brian Chmiel, Moshe Island, Ron Banner, Seffi Naor, Daniel Soudry
Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N: M Transposable Masks. CoRR (2021)
Niv Giladi, Zvika Ben-Haim, Sella Nevo, Yossi Matias, Daniel Soudry
Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling. NeurIPS (2021)
Brian Chmiel, Ron Banner, Elad Hoffer, Hilla Ben-Yaacov, Daniel Soudry
Logarithmic Unbiased Quantization: Practical 4-bit Training in Deep Learning. CoRR (2021)
Rotem Mulayoff, Tomer Michaeli, Daniel Soudry
The Implicit Bias of Minima Stability: A View from Function Space. NeurIPS (2021)
Itay Hubara, Brian Chmiel, Moshe Island, Ron Banner, Joseph Naor, Daniel Soudry
Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N: M Transposable Masks. NeurIPS (2021)
Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
Kernel and Rich Regimes in Overparametrized Models. CoRR (2020)
Matan Haroush, Itay Hubara, Elad Hoffer, Daniel Soudry
The Knowledge Within: Methods for Data-Free Model Compression. CVPR (2020)
Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? ICML (2020)
Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, Daniel Soudry
Augment Your Batch: Improving Generalization Through Instance Repetition. CVPR (2020)
Zhihui Zhu, Daniel Soudry, Yonina C. Eldar, Michael B. Wakin
The Global Optimization Geometry of Shallow Linear Neural Networks. J. Math. Imaging Vis. 62 (3) (2020)
Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates. CoRR (2020)
Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro
A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case. ICLR (2020)
Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? CoRR (2020)
Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? ICLR (2020)
Edward Moroshko, Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Nati Srebro, Daniel Soudry
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. NeurIPS (2020)
Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, Daniel Soudry
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming. CoRR (2020)
Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry
Neural gradients are lognormally distributed: understanding sparse and quantized training. CoRR (2020)
Edward Moroshko, Suriya Gunasekar, Blake E. Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. CoRR (2020)
Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
Kernel and Rich Regimes in Overparametrized Models. COLT (2020)
Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, Daniel Soudry
Augment your batch: better training with larger batches. CoRR (2019)
Pedro Savarese, Itay Evron, Daniel Soudry, Nathan Srebro
How do infinite width bounded norm networks look in function space? CoRR (2019)
Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. CoRR (2019)
Elad Hoffer, Berry Weinstein, Itay Hubara, Tal Ben-Nun, Torsten Hoefler, Daniel Soudry
Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency. CoRR (2019)
Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? CoRR (2019)
Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off. CoRR (2019)
Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro
A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case. CoRR (2019)
Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Pedro Henrique Pamplona Savarese, Nathan Srebro, Daniel Soudry
Convergence of Gradient Descent on Separable Data. AISTATS (2019)
Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. ICML (2019)
Pedro Savarese, Itay Evron, Daniel Soudry, Nathan Srebro
How do infinite width bounded norm networks look in function space? COLT (2019)
Matan Haroush, Itay Hubara, Elad Hoffer, Daniel Soudry
The Knowledge Within: Methods for Data-Free Model Compression. CoRR (2019)
Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off. NeurIPS (2019)
Mor Shpigel Nacson, Nathan Srebro, Daniel Soudry
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate. AISTATS (2019)
Tzofnat Greenberg-Toledo, Ben Perach, Daniel Soudry, Shahar Kvatinsky
MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks. CoRR (2019)
Ron Banner, Yury Nahshan, Daniel Soudry
Post training 4-bit quantization of convolutional networks for rapid-deployment. NeurIPS (2019)
Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
Scalable methods for 8-bit training of neural networks. NeurIPS (2018)
Ron Banner, Yury Nahshan, Elad Hoffer, Daniel Soudry
ACIQ: Analytical Clipping for Integer Quantization of neural networks. CoRR (2018)
Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro
Implicit Bias of Gradient Descent on Linear Convolutional Networks. NeurIPS (2018)
Daniel Soudry, Elad Hoffer
Exponentially vanishing sub-optimal local minima in multilayer neural networks. ICLR (Workshop) (2018)
Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
Bayesian Gradient Descent: Online Variational Bayes Learning with Increased Robustness to Catastrophic Forgetting and Weight Pruning. CoRR (2018)
Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
Implicit Bias of Gradient Descent on Linear Convolutional Networks. CoRR (2018)
Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
Characterizing Implicit Bias in Terms of Optimization Geometry. CoRR (2018)
Mor Shpigel Nacson, Nathan Srebro, Daniel Soudry
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate. CoRR (2018)
Elad Hoffer, Ron Banner, Itay Golan, Daniel Soudry
Norm matters: efficient and accurate normalization schemes in deep networks. CoRR (2018)
Philippa J. Karoly, Levin Kuhlmann, Daniel Soudry, David B. Grayden, Mark J. Cook, Dean R. Freestone
Seizure pathways: A model-based investigation. PLoS Comput. Biol. 14 (10) (2018)
Elad Hoffer, Ron Banner, Itay Golan, Daniel Soudry
Norm matters: efficient and accurate normalization schemes in deep networks. NeurIPS (2018)
Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
Scalable Methods for 8-bit Training of Neural Networks. CoRR (2018)
Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Nathan Srebro
The Implicit Bias of Gradient Descent on Separable Data. ICLR (Poster) (2018)
Elad Hoffer, Itay Hubara, Daniel Soudry
Fix your classifier: the marginal value of training the last weight layer. ICLR (Poster) (2018)
Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
Characterizing Implicit Bias in Terms of Optimization Geometry. ICML (2018)
Elad Hoffer, Itay Hubara, Daniel Soudry
Fix your classifier: the marginal value of training the last weight layer. CoRR (2018)
Zhihui Zhu, Daniel Soudry, Yonina C. Eldar, Michael B. Wakin
The Global Optimization Geometry of Shallow Linear Neural Networks. CoRR (2018)
Elad Hoffer, Shai Fine, Daniel Soudry
On the Blindspots of Convolutional Networks. CoRR (2018)
Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Suriya Gunasekar, Nathan Srebro
The Implicit Bias of Gradient Descent on Separable Data. J. Mach. Learn. Res. 19 (2018)
Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Nathan Srebro, Daniel Soudry
Convergence of Gradient Descent on Separable Data. CoRR (2018)
Daniel Soudry, Elad Hoffer, Nathan Srebro
The Implicit Bias of Gradient Descent on Separable Data. CoRR (2017)
Elad Hoffer, Itay Hubara, Daniel Soudry
Train longer, generalize better: closing the generalization gap in large batch training of neural networks. CoRR (2017)
Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. J. Mach. Learn. Res. 18 (2017)
Elad Hoffer, Itay Hubara, Daniel Soudry
Train longer, generalize better: closing the generalization gap in large batch training of neural networks. NIPS (2017)
Johannes Friedrich, Weijian Yang, Daniel Soudry, Yu Mu, Misha Ahrens, Rafael Yuste, Darcy S. Peterka, Liam Paninski
Multi-scale approaches for high-speed imaging and analysis of large neural populations. PLoS Comput. Biol. 13 (8) (2017)
Daniel Soudry, Yair Carmon
No bad local minima: Data independent training error guarantees for multilayer neural networks. CoRR (2016)
Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
Binarized Neural Networks. NIPS (2016)
Eyal Rosenthal, Sergey Greshnikov, Daniel Soudry, Shahar Kvatinsky
A fully analog memristor-based neural network with online gradient training. ISCAS (2016)

Daniel Soudry.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Daniel Soudry