research
∙
02/16/2022
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
Pruning neural networks at initialization would enable us to find sparse...
share
research
∙
01/30/2022
COIN++: Data Agnostic Neural Compression
Neural compression algorithms are typically based on autoencoders that r...
research
∙
03/03/2021
COIN: COmpression with Implicit Neural representations
We propose a new simple approach for image compression: instead of stori...
research
∙
07/01/2020
Single Shot Structured Pruning Before Training
We introduce a method to speed up training by 2x and inference by 3x in ...
research
∙
02/18/2020
Gradient ℓ_1 Regularization for Quantization Robustness
We analyze the effect of quantizing weights and activations of neural ne...
research
∙
12/22/2019