28 citations · 58 across the 6 of their papers we have counts for
4 papers · 1 filter
Efficient Forward Architecture Search
Hanzhang Hu, John Langford, Rich Caruana +3
We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. The added shortcut connections effectively p…
Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing
Hanzhang Hu, Debadeepta Dey, Martial Hebert +1
This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via \emph{anytime} predictions from auxiliary predictions. Specif…
Gradient Boosting on Stochastic Data Streams
Hanzhang Hu, Wen Sun, Arun Venkatraman +2
Boosting is a popular ensemble algorithm that generates more powerful learners by linearly combining base models from a simpler hypothesis class. In this work, we investigate the p…
Efficient Feature Group Sequencing for Anytime Linear Prediction
Hanzhang Hu, Alexander Grubb, J. Andrew Bagnell +1
We consider \textit{anytime} linear prediction in the common machine learning setting, where features are in groups that have costs. We achieve anytime (or interruptible) predictio…