41 citations · 82 across the 9 of their papers we have counts for
10 papers
DyRep: Bootstrapping Training with Dynamic Re-parameterization
Tao Huang, Shan You, Bohan Zhang +4
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize all op…
Relational Surrogate Loss Learning
Tao Huang, Zekang Li, Hua Lu +6
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. Thi…
Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning
Tao Huang, Jiachen Wang, Xiao Chen
Learning informative representations from image-based observations is of fundamental concern in deep Reinforcement Learning (RL). However, data-inefficiency remains a significant b…
Gradient Boosted Binary Histogram Ensemble for Large-scale Regression
Hanyuan Hang, Tao Huang, Yuchao Cai +2
In this paper, we propose a gradient boosting algorithm for large-scale regression problems called \textit{Gradient Boosted Binary Histogram Ensemble} (GBBHE) based on binary histo…
Prioritized Architecture Sampling with Monto-Carlo Tree Search
Xiu Su, Tao Huang, Yanxi Li +5
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once. Ho…
Locally Free Weight Sharing for Network Width Search
Xiu Su, Shan You, Tao Huang +4
Searching for network width is an effective way to slim deep neural networks with hardware budgets. With this aim, a one-shot supernet is usually leveraged as a performance evaluat…