30 citations · 65 across the 6 of their papers we have counts for
4 papers · 1 filter
See through Gradients: Image Batch Recovery via GradInversion
Hongxu Yin, Arun Mallya, Arash Vahdat +3
Training deep neural networks requires gradient estimation from data batches to update parameters. Gradients per parameter are averaged over a set of data and this has been presume…
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
Hongxu Yin, Pavlo Molchanov, Zhizhong Li +5
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthes…
UNAS: Differentiable Architecture Search Meets Reinforcement Learning
Arash Vahdat, Arun Mallya, Ming-Yu Liu +1
Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demons…
Importance Estimation for Neural Network Pruning
Pavlo Molchanov, Arun Mallya, Stephen Tyree +2
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution o…