Search Results for author:
Found 8 papers, 5 papers with code
Hacking Generative Models with Differentiable Network Bending
In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective.
SPADE: Sparsity-Guided Debugging for Deep Neural Networks
Towards this goal, multiple tools have been proposed to aid a human examiner in reasoning about a network's behavior in general or on a set of instances.
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization
Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the community.
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
Pruning - that is, setting a significant subset of the parameters of a neural network to zero - is one of the most popular methods of model compression.
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks
We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse.
How Well Do Sparse Imagenet Models Transfer?
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets.
AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
The increasing computational requirements of deep neural networks (DNNs) have led to significant interest in obtaining DNN models that are sparse, yet accurate.
Ranked #1 on
Network Pruning
on CIFAR-100
FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data
In this work we address the problem of fair learning from unreliable training data in the robust multisource setting, where the available training data comes from multiple sources, a fraction of which might not be representative of the true data distribution.
