3 papers
cs.LG2018
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent
Noah Golmant, Nikita Vemuri, Zhewei Yao +5
Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and syste…
stat.ML2018
Transfer Learning for Estimating Causal Effects using Neural Networks
Sören R. Künzel, Bradly C. Stadie, Nikita Vemuri +3
We develop new algorithms for estimating heterogeneous treatment effects, combining recent developments in transfer learning for neural networks with insights from the causal infer…
cs.LG2018
Targeted Adversarial Examples for Black Box Audio Systems
Rohan Taori, Amog Kamsetty, Brenton Chu +1
The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adver…