Brian Chmiel

Appl. Intell., April, 2023

Minimum Variance Unbiased N: M Sparsity for the Neural Gradients.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Bimodal Distributed Binarized Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2022

Optimal Fine-Grained N: M sparsity for Activations and Neural Gradients.

[BibT_eX]

[DOI]

CoRR, 2022

2021

Loss aware post-training quantization.

[BibT_eX]

[DOI]

Yury Nahshan

Ron Banner

Alex M. Bronstein

Mach. Learn., 2021

CAT: Compression-Aware Training for bandwidth reduction.

[BibT_eX]

[DOI]

Ron Banner

Alex M. Bronstein

J. Mach. Learn. Res., 2021

Logarithmic Unbiased Quantization: Practical 4-bit Training in Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N: M Transposable Masks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural gradients are near-lognormal: improved quantized and sparse training.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Neural gradients are lognormally distributed: understanding sparse and quantized training.

[BibT_eX]

[DOI]

CoRR, 2020

Colored Noise Injection for Training Adversarially Robust Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2020

Robust Quantization: One Model to Rule Them All.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Feature Map Transform Coding for Energy-Efficient CNN Inference.

[BibT_eX]

[DOI]

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

2019

Smoothed Inference for Adversarially-Trained Models.

[BibT_eX]

[DOI]

Yaniv Nemcovsky

Alexander M. Bronstein

CoRR, 2019

Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks.

[BibT_eX]

[DOI]

Yochai Zur

Itay Evron

Alexander M. Bronstein