87 citations · 240 across the 13 of their papers we have counts for
6 papers · 1 filter
Optimizing Data Collection for Machine Learning
Rafid Mahmood, James Lucas, Jose M. Alvarez +2
Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting dat…
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…
Personalized Federated Learning with First Order Model Optimization
Michael Zhang, Karan Sapra, Sanja Fidler +2
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients. Her…
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…
Training Data Subset Search with Ensemble Active Learning
Kashyap Chitta, Jose M. Alvarez, Elmar Haussmann +1
Deep Neural Networks (DNNs) often rely on very large datasets for training. Given the large size of such datasets, it is conceivable that they contain certain samples that either d…
The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
Jiaming Zeng, Adam Lesnikowski, Jose M. Alvarez
One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural n…