activity
20152021
most citedToward Robustness against Label Noise in Training Deep Discriminative Neural Networks

119 citations · 170 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG202130 cited

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…

cs.LG2020

A Contrastive Learning Approach for Training Variational Autoencoder Priors

Jyoti Aneja, Alexander Schwing, Jan Kautz +1

Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. However, they struggle to generate high-quality images…

cs.LG2020

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

Zhisheng Xiao, Karsten Kreis, Jan Kautz +1

Energy-based models (EBMs) have recently been successful in representing complex distributions of small images. However, sampling from them requires expensive Markov chain Monte Ca…

cs.LG2020

On the distance between two neural networks and the stability of learning

Jeremy Bernstein, Arash Vahdat, Yisong Yue +1

This paper relates parameter distance to gradient breakdown for a broad class of nonlinear compositional functions. The analysis leads to a new distance function called deep relati…

cs.LG2019

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…

cs.LG2019

A Robust Learning Approach to Domain Adaptive Object Detection

Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar +1

Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which c…