1.9k citations · 4.9k across the 47 of their papers we have counts for
15 papers · 1 filter
Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning
Qisen Yang, Huanqian Wang, Mukun Tong +3
The black-box nature of deep reinforcement learning (RL) hinders them from real-world applications. Therefore, interpreting and explaining RL agents have been active research topic…
Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance
Qisen Yang, Shenzhi Wang, Qihang Zhang +2
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributiona…
Boosted Dynamic Neural Networks
Haichao Yu, Haoxiang Li, Gang Hua +2
Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different la…
Evolving Attention with Residual Convolutions
Yujing Wang, Yaming Yang, Jiangang Bai +6
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model…
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
Yulin Wang, Jiayi Guo, Shiji Song +1
Deep learning based semi-supervised learning (SSL) algorithms have led to promising results in recent years. However, they tend to introduce multiple tunable hyper-parameters, maki…
Cross-Iteration Batch Normalization
Zhuliang Yao, Yue Cao, Shuxin Zheng +2
A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics…
Convolutional Networks with Dense Connectivity
Gao Huang, Zhuang Liu, Geoff Pleiss +2
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the…
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Wenjie Shi, Shiji Song, Hui Wu +3
Model-free deep reinforcement learning (RL) algorithms have been widely used for a range of complex control tasks. However, slow convergence and sample inefficiency remain challeng…
Asymmetric Valleys: Beyond Sharp and Flat Local Minima
Haowei He, Gao Huang, Yang Yuan
Despite the non-convex nature of their loss functions, deep neural networks are known to generalize well when optimized with stochastic gradient descent (SGD). Recent work conjectu…
Gradient Boosted Feature Selection
Zhixiang Eddie Xu, Gao Huang, Kilian Q. Weinberger +1
A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with t…
Rethinking the Value of Network Pruning
Zhuang Liu, Mingjie Sun, Tinghui Zhou +2
Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training…
An empirical study on evaluation metrics of generative adversarial networks
Qiantong Xu, Gao Huang, Yang Yuan +4
Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address…
Snapshot Ensembles: Train 1, get M for free
Gao Huang, Yixuan Li, Geoff Pleiss +3
Ensembles of neural networks are known to be much more robust and accurate than individual networks. However, training multiple deep networks for model averaging is computationally…
Multi-Scale Dense Networks for Resource Efficient Image Classification
Gao Huang, Danlu Chen, Tianhong Li +3
In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction…
Deep Networks with Stochastic Depth
Gao Huang, Yu Sun, Zhuang Liu +2
Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many la…