28 citations · 58 across the 6 of their papers we have counts for
6 papers
On Optimal Convergence Rates for the Nonlinear Schrödinger Equation with a Wave Operator via Localized Orthogonal Decomposition
Hanzhang Hu, Zetao Ma, Lei Zhang
In this paper, we develop a Localized Orthogonal Decomposition (LOD) method for the two-dimensional time-dependent nonlinear Schrödinger equation with a wave operator. We prove tha…
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…
Log-DenseNet: How to Sparsify a DenseNet
Hanzhang Hu, Debadeepta Dey, Allison Del Giorno +2
Skip connections are increasingly utilized by deep neural networks to improve accuracy and cost-efficiency. In particular, the recent DenseNet is efficient in computation and param…
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…