Daniel Soudry - RankMe

134 papers A* 43A 3C 1Journal 80Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Optimal L2 Regularization in High-dimensional Continual Linear Regression. CoRR Gilad Karpel, Edward Moroshko, Ran Levinstein, Ron Meir, Daniel Soudry, Itay Evron
2025	J	`jnl`	Alias-Free ViT: Fractional Shift Invariance via Linear Attention. CoRR Hagay Michaeli, Daniel Soudry
2025	J	`jnl`	Are Greedy Task Orderings Better Than Random in Continual Linear Regression? CoRR Matan Tsipory, Ran Levinstein, Itay Evron, Mark Kong, Deanna Needell, Daniel Soudry
2025	J	`jnl`	Better Rates for Random Task Orderings in Continual Linear Models. CoRR Itay Evron, Ran Levinstein, Matan Schliserman, Uri Sherman, Tomer Koren, Daniel Soudry, Nathan Srebro
2025	J	`jnl`	Block Sparse Flash Attention. CoRR Daniel Ohayon, Itay Lamprecht, Itay Hubara, Israel Cohen, Daniel Soudry, Noam Elata
2025	J	`jnl`	FP4 All the Way: Fully Quantized Training of LLMs. CoRR Brian Chmiel, Maxim Fishman, Ron Banner, Daniel Soudry
2025	J	`jnl`	Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks. Trans. Mach. Learn. Res. Edan Kinderman, Itay Hubara, Haggai Maron, Daniel Soudry
2025	J	`jnl`	Optimal Rates in Continual Linear Regression via Increasing Regularization. CoRR Ran Levinstein, Amit Attia, Matan Schliserman, Uri Sherman, Tomer Koren, Daniel Soudry, Itay Evron
2025	J	`jnl`	PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training. CoRR Matan Haroush, Daniel Soudry
2025	A*	`conf`	Scaling FP8 training to trillion-token LLMs. ICLR Maxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry
2025	J	`jnl`	Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes. CoRR Itamar Harel, Yonathan Wolanowsky, Gal Vardi, Nathan Srebro, Daniel Soudry
2025	J	`jnl`	Tensor-Parallelism with Partially Synchronized Activations. CoRR Itay Lamprecht, Asaf Karnieli, Yair Hanani, Niv Giladi, Daniel Soudry
2025	A*	`conf`	When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets. ICML Chen Zeno, Hila Manor, Greg Ongie, Nir Weinberger, Tomer Michaeli, Daniel Soudry
2025	J	`jnl`	When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets. CoRR Chen Zeno, Hila Manor, Greg Ongie, Nir Weinberger, Tomer Michaeli, Daniel Soudry
2024	A*	`conf`	Exponential Quantum Communication Advantage in Distributed Inference and Learning. NeurIPS Dar Gilboa, Hagay Michaeli, Daniel Soudry, Jarrod R. McClean
2024	J	`jnl`	Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks. CoRR Edan Kinderman, Itay Hubara, Haggai Maron, Daniel Soudry
2024	A*	`conf`	How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers. ICML Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson, Alon Brutzkus, Nathan Srebro, Daniel Soudry
2024	J	`jnl`	How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers. CoRR Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson, Alon Brutzkus, Nathan Srebro, Daniel Soudry
2024	A*	`conf`	Provable Tempered Overfitting of Minimal Nets and Typical Nets. NeurIPS Itamar Harel, William Hoza, Gal Vardi, Itay Evron, Nati Srebro, Daniel Soudry
2024	J	`jnl`	Provable Tempered Overfitting of Minimal Nets and Typical Nets. CoRR Itamar Harel, William M. Hoza, Gal Vardi, Itay Evron, Nathan Srebro, Daniel Soudry
2024	J	`jnl`	Scaling FP8 training to trillion-token LLMs. CoRR Maxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry
2024	A*	`conf`	Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes. NeurIPS Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang
2024	J	`jnl`	Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes. CoRR Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang
2024	A*	`conf`	The Implicit Bias of Gradient Descent on Separable Multiclass Data. NeurIPS Hrithik Ravi, Clayton Scott, Daniel Soudry, Yutong Wang
2024	J	`jnl`	The Implicit Bias of Gradient Descent on Separable Multiclass Data. CoRR Hrithik Ravi, Clayton Scott, Daniel Soudry, Yutong Wang
2024	A*	`conf`	The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical Model. ICLR Daniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry, Paul Hand
2024	J	`jnl`	The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical Model. CoRR Daniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry, Paul Hand
2024	A*	`conf`	Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators. ICLR Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
2024	J	`jnl`	Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators. CoRR Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
2023	A*	`conf`	Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats. ICLR Brian Chmiel, Ron Banner, Elad Hoffer, Hilla Ben-Yaacov, Daniel Soudry
2023	A*	`conf`	Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations. CVPR Hagay Michaeli, Tomer Michaeli, Daniel Soudry
2023	J	`jnl`	Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations. CoRR Hagay Michaeli, Tomer Michaeli, Daniel Soudry
2023	A*	`conf`	Continual Learning in Linear Classification on Separable Data. ICML Itay Evron, Edward Moroshko, Gon Buzaglo, Maroun Khriesh, Badea Marjieh, Nathan Srebro, Daniel Soudry
2023	J	`jnl`	Continual Learning in Linear Classification on Separable Data. CoRR Itay Evron, Edward Moroshko, Gon Buzaglo, Maroun Khriesh, Badea Marjieh, Nathan Srebro, Daniel Soudry
2023	A*	`conf`	DropCompute: simple and more robust distributed synchronous training via compute variance reduction. NeurIPS Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer, Kfir Y. Levy, Daniel Soudry
2023	J	`jnl`	DropCompute: simple and more robust distributed synchronous training via compute variance reduction. CoRR Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer, Kfir Yehuda Levy, Daniel Soudry
2023	A*	`conf`	Explore to Generalize in Zero-Shot RL. NeurIPS Ev Zisselman, Itai Lavie, Daniel Soudry, Aviv Tamar
2023	J	`jnl`	Explore to Generalize in Zero-Shot RL. CoRR Ev Zisselman, Itai Lavie, Daniel Soudry, Aviv Tamar
2023	A*	`conf`	Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. ICML Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
2023	J	`jnl`	Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. CoRR Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
2023	A*	`conf`	How do Minimum-Norm Shallow Denoisers Look in Function Space? NeurIPS Chen Zeno, Greg Ongie, Yaniv Blumenfeld, Nir Weinberger, Daniel Soudry
2023	J	`jnl`	How do Minimum-Norm Shallow Denoisers Look in Function Space? CoRR Chen Zeno, Greg Ongie, Yaniv Blumenfeld, Nir Weinberger, Daniel Soudry
2023	A*	`conf`	Minimum Variance Unbiased N: M Sparsity for the Neural Gradients. ICLR Brian Chmiel, Itay Hubara, Ron Banner, Daniel Soudry
2023	A*	`conf`	The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks. ICLR Mor Shpigel Nacson, Rotem Mulayoff, Greg Ongie, Tomer Michaeli, Daniel Soudry
2023	J	`jnl`	The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks. CoRR Mor Shpigel Nacson, Rotem Mulayoff, Greg Ongie, Tomer Michaeli, Daniel Soudry
2023	A	`conf`	The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study. AISTATS Itay Evron, Ophir Onn, Tamar Weiss Orzech, Hai Azeroual, Daniel Soudry
2023	J	`jnl`	The Role of Codeword-to-Class Assignments in Error-Correcting Codes: An Empirical Study. CoRR Itay Evron, Ophir Onn, Tamar Weiss Orzech, Hai Azeroual, Daniel Soudry
2022	A*	`conf`	A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks. ICLR Matan Haroush, Tzviel Frostig, Ruth Heller, Daniel Soudry
2022	A*	`conf`	How catastrophic can catastrophic forgetting be in linear regression? COLT Itay Evron, Edward Moroshko, Rachel A. Ward, Nathan Srebro, Daniel Soudry
2022	J	`jnl`	How catastrophic can catastrophic forgetting be in linear regression? CoRR Itay Evron, Edward Moroshko, Rachel A. Ward, Nati Srebro, Daniel Soudry
2022	A*	`conf`	Implicit Bias of the Step Size in Linear Diagonal Neural Networks. ICML Mor Shpigel Nacson, Kavya Ravichandran, Nathan Srebro, Daniel Soudry
2022	J	`jnl`	Optimal Fine-Grained N: M sparsity for Activations and Neural Gradients. CoRR Brian Chmiel, Itay Hubara, Ron Banner, Daniel Soudry
2022	A*	`conf`	Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability. AAAI Aviv Tamar, Daniel Soudry, Ev Zisselman
2021	A*	`conf`	Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N: M Transposable Masks. NeurIPS Itay Hubara, Brian Chmiel, Moshe Island, Ron Banner, Joseph Naor, Daniel Soudry
2021	J	`jnl`	Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N: M Transposable Masks. CoRR Itay Hubara, Brian Chmiel, Moshe Island, Ron Banner, Seffi Naor, Daniel Soudry
2021	A*	`conf`	Accurate Post Training Quantization With Small Calibration Sets. ICML Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, Daniel Soudry
2021	J	`jnl`	Logarithmic Unbiased Quantization: Practical 4-bit Training in Deep Learning. CoRR Brian Chmiel, Ron Banner, Elad Hoffer, Hilla Ben-Yaacov, Daniel Soudry
2021	A*	`conf`	Neural gradients are near-lognormal: improved quantized and sparse training. ICLR Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry
2021	A*	`conf`	On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent. ICML Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake E. Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry
2021	J	`jnl`	On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent. CoRR Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake E. Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry
2021	A*	`conf`	Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling. NeurIPS Niv Giladi, Zvika Ben-Haim, Sella Nevo, Yossi Matias, Daniel Soudry
2021	J	`jnl`	Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling. CoRR Niv Giladi, Zvika Ben-Haim, Sella Nevo, Yossi Matias, Daniel Soudry
2021	J	`jnl`	Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability. CoRR Aviv Tamar, Daniel Soudry, Ev Zisselman
2021	J	`jnl`	Statistical Testing for Efficient Out of Distribution Detection in Deep Neural Networks. CoRR Matan Haroush, Tzviel Frostig, Ruth Heller, Daniel Soudry
2021	J	`jnl`	Task-Agnostic Continual Learning Using Online Variational Bayes With Fixed-Point Updates. Neural Comput. Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
2021	A*	`conf`	The Implicit Bias of Minima Stability: A View from Function Space. NeurIPS Rotem Mulayoff, Tomer Michaeli, Daniel Soudry
2020	A*	`conf`	A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case. ICLR Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro
2020	A*	`conf`	At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? ICLR Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry
2020	A*	`conf`	Augment Your Batch: Improving Generalization Through Instance Repetition. CVPR Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, Daniel Soudry
2020	A*	`conf`	Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? ICML Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
2020	J	`jnl`	Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? CoRR Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
2020	A*	`conf`	Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. NeurIPS Edward Moroshko, Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Nati Srebro, Daniel Soudry
2020	J	`jnl`	Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. CoRR Edward Moroshko, Suriya Gunasekar, Blake E. Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry
2020	J	`jnl`	Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming. CoRR Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, Daniel Soudry
2020	A*	`conf`	Kernel and Rich Regimes in Overparametrized Models. COLT Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
2020	J	`jnl`	Kernel and Rich Regimes in Overparametrized Models. CoRR Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
2020	J	`jnl`	Neural gradients are lognormally distributed: understanding sparse and quantized training. CoRR Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry
2020	J	`jnl`	Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates. CoRR Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
2020	J	`jnl`	The Global Optimization Geometry of Shallow Linear Neural Networks. J. Math. Imaging Vis. Zhihui Zhu, Daniel Soudry, Yonina C. Eldar, Michael B. Wakin
2020	A*	`conf`	The Knowledge Within: Methods for Data-Free Model Compression. CVPR Matan Haroush, Itay Hubara, Elad Hoffer, Daniel Soudry
2019	J	`jnl`	A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case. CoRR Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro
2019	A*	`conf`	A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off. NeurIPS Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
2019	J	`jnl`	A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off. CoRR Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
2019	J	`jnl`	At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? CoRR Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry
2019	J	`jnl`	Augment your batch: better training with larger batches. CoRR Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, Daniel Soudry
2019	A	`conf`	Convergence of Gradient Descent on Separable Data. AISTATS Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Pedro Henrique Pamplona Savarese, Nathan Srebro, Daniel Soudry
2019	A*	`conf`	How do infinite width bounded norm networks look in function space? COLT Pedro Savarese, Itay Evron, Daniel Soudry, Nathan Srebro
2019	J	`jnl`	How do infinite width bounded norm networks look in function space? CoRR Pedro Savarese, Itay Evron, Daniel Soudry, Nathan Srebro
2019	A*	`conf`	Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. ICML Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
2019	J	`jnl`	Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. CoRR Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
2019	J	`jnl`	MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks. CoRR Tzofnat Greenberg-Toledo, Ben Perach, Daniel Soudry, Shahar Kvatinsky
2019	J	`jnl`	Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency. CoRR Elad Hoffer, Berry Weinstein, Itay Hubara, Tal Ben-Nun, Torsten Hoefler, Daniel Soudry
2019	A*	`conf`	Post training 4-bit quantization of convolutional networks for rapid-deployment. NeurIPS Ron Banner, Yury Nahshan, Daniel Soudry
2019	A	`conf`	Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate. AISTATS Mor Shpigel Nacson, Nathan Srebro, Daniel Soudry
2019	J	`jnl`	The Knowledge Within: Methods for Data-Free Model Compression. CoRR Matan Haroush, Itay Hubara, Elad Hoffer, Daniel Soudry
2018	J	`jnl`	ACIQ: Analytical Clipping for Integer Quantization of neural networks. CoRR Ron Banner, Yury Nahshan, Elad Hoffer, Daniel Soudry
2018	J	`jnl`	Bayesian Gradient Descent: Online Variational Bayes Learning with Increased Robustness to Catastrophic Forgetting and Weight Pruning. CoRR Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry
2018	A*	`conf`	Characterizing Implicit Bias in Terms of Optimization Geometry. ICML Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	J	`jnl`	Characterizing Implicit Bias in Terms of Optimization Geometry. CoRR Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	J	`jnl`	Convergence of Gradient Descent on Separable Data. CoRR Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Nathan Srebro, Daniel Soudry
2018	—	`conf`	Exponentially vanishing sub-optimal local minima in multilayer neural networks. ICLR (Workshop) Daniel Soudry, Elad Hoffer
2018	—	`conf`	Fix your classifier: the marginal value of training the last weight layer. ICLR (Poster) Elad Hoffer, Itay Hubara, Daniel Soudry
2018	J	`jnl`	Fix your classifier: the marginal value of training the last weight layer. CoRR Elad Hoffer, Itay Hubara, Daniel Soudry
2018	A*	`conf`	Implicit Bias of Gradient Descent on Linear Convolutional Networks. NeurIPS Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro
2018	J	`jnl`	Implicit Bias of Gradient Descent on Linear Convolutional Networks. CoRR Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	A*	`conf`	Norm matters: efficient and accurate normalization schemes in deep networks. NeurIPS Elad Hoffer, Ron Banner, Itay Golan, Daniel Soudry
2018	J	`jnl`	Norm matters: efficient and accurate normalization schemes in deep networks. CoRR Elad Hoffer, Ron Banner, Itay Golan, Daniel Soudry
2018	J	`jnl`	On the Blindspots of Convolutional Networks. CoRR Elad Hoffer, Shai Fine, Daniel Soudry
2018	J	`jnl`	Scalable Methods for 8-bit Training of Neural Networks. CoRR Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
2018	A*	`conf`	Scalable methods for 8-bit training of neural networks. NeurIPS Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
2018	J	`jnl`	Seizure pathways: A model-based investigation. PLoS Comput. Biol. Philippa J. Karoly, Levin Kuhlmann, Daniel Soudry, David B. Grayden, Mark J. Cook, Dean R. Freestone
2018	J	`jnl`	Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate. CoRR Mor Shpigel Nacson, Nathan Srebro, Daniel Soudry
2018	J	`jnl`	The Global Optimization Geometry of Shallow Linear Neural Networks. CoRR Zhihui Zhu, Daniel Soudry, Yonina C. Eldar, Michael B. Wakin
2018	—	`conf`	The Implicit Bias of Gradient Descent on Separable Data. ICLR (Poster) Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Nathan Srebro
2018	J	`jnl`	The Implicit Bias of Gradient Descent on Separable Data. J. Mach. Learn. Res. Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Suriya Gunasekar, Nathan Srebro
2017	J	`jnl`	Multi-scale approaches for high-speed imaging and analysis of large neural populations. PLoS Comput. Biol. Johannes Friedrich, WeiJian Yang, Daniel Soudry, Yu Mu, Misha B. Ahrens, Rafael Yuste, Darcy S. Peterka, Liam Paninski
2017	J	`jnl`	Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. J. Mach. Learn. Res. Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
2017	J	`jnl`	The Implicit Bias of Gradient Descent on Separable Data. CoRR Daniel Soudry, Elad Hoffer, Nathan Srebro
2017	—	`conf`	Train longer, generalize better: closing the generalization gap in large batch training of neural networks. NIPS Elad Hoffer, Itay Hubara, Daniel Soudry
2017	J	`jnl`	Train longer, generalize better: closing the generalization gap in large batch training of neural networks. CoRR Elad Hoffer, Itay Hubara, Daniel Soudry
2016	C	`conf`	A fully analog memristor-based neural network with online gradient training. ISCAS Eyal Rosenthal, Sergey Greshnikov, Daniel Soudry, Shahar Kvatinsky
2016	—	`conf`	Binarized Neural Networks. NIPS Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
2016	J	`jnl`	No bad local minima: Data independent training error guarantees for multilayer neural networks. CoRR Daniel Soudry, Yair Carmon
2016	J	`jnl`	Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. CoRR Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
2015	J	`jnl`	Efficient "Shotgun" Inference of Neural Connectivity from Highly Sub-sampled Activity Data. PLoS Comput. Biol. Daniel Soudry, Suraj Keshri, Patrick Stinson, Min-hwan Oh, Garud Iyengar, Liam Paninski
2015	J	`jnl`	Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training. IEEE Trans. Neural Networks Learn. Syst. Daniel Soudry, Dotan Di Castro, Asaf Gal, Avinoam Kolodny, Shahar Kvatinsky
2015	J	`jnl`	Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation. CoRR Zhiyong Cheng, Daniel Soudry, Zexi Mao, Zhen-Zhong Lan
2014	J	`jnl`	Diffusion approximation-based simulation of stochastic ion channels: which method to use? Frontiers Comput. Neurosci. Danilo Pezo, Daniel Soudry, Patricio Orio
2014	—	`conf`	Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights. NIPS Daniel Soudry, Itay Hubara, Ron Meir
2014	J	`jnl`	The neuronal response at extended timescales: a linearized spiking input-output relation. Frontiers Comput. Neurosci. Daniel Soudry, Ron Meir
2014	J	`jnl`	The neuronal response at extended timescales: long-term correlations without long-term memory. Frontiers Comput. Neurosci. Daniel Soudry, Ron Meir
2012	—	`conf`	"Neuronal spike generation mechanism as an oversampling, noise-shaping A-to-D converter". NIPS Dmitri B. Chklovskii, Daniel Soudry
2012	J	`jnl`	Conductance-Based Neuron Models and the Slow Dynamics of Excitability. Frontiers Comput. Neurosci. Daniel Soudry, Ron Meir
2010	J	`jnl`	History-Dependent Dynamics in a Generic Model of Ion Channels - An Analytic Study. Frontiers Comput. Neurosci. Daniel Soudry, Ron Meir