activity
20182021
most citedDynamical Isometry and a Mean Field Theory of LSTMs and GRUs

24 citations · 33 across the 4 of their papers we have counts for

collaborators

7 papers

stat.ML20211 cited

Deep Networks Provably Classify Data on Curves

Tingran Wang, Sam Buchanan, Dar Gilboa +1

Data with low-dimensional nonlinear structure are ubiquitous in engineering and scientific problems. We study a model problem with such structure -- a binary classification task th…

cs.LG20205 cited

Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?

Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity…

cs.LG2019

Is Feature Diversity Necessary in Neural Network Initialization?

Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initializa…

cs.LG20193 cited

Wider Networks Learn Better Features

Dar Gilboa, Guy Gur-Ari

Transferability of learned features between tasks can massively reduce the cost of training a neural network on a novel task. We investigate the effect of network width on learned…

stat.ML2019

A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off

Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Reducing the precision of weights and activation functions in neural network training, with minimal impact on performance, is essential for the deployment of these models in resour…

cs.LG201924 cited

Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs

Dar Gilboa, Bo Chang, Minmin Chen +4

Training recurrent neural networks (RNNs) on long sequence tasks is plagued with difficulties arising from the exponential explosion or vanishing of signals as they propagate forwa…