779 citations
- Massachusetts Institute of TechnologyUS13 papers
- Harvard UniversityUS10 papers
- Stanford UniversityUS10 papers
- Technical University of MunichDE9 papers
- Beijing Academy of Artificial IntelligenceCN8 papers
- Monash UniversityAU8 papers
- Shanghai Jiao Tong UniversityCN8 papers
- University of Hong KongHK8 papers
- Harvard University PressUS7 papers
- University of Southern CaliforniaUS7 papers
- Hong Kong University of Science and TechnologyHK6 papers
- Imperial College LondonGB6 papers
9 papers · 2 filters
An Off-policy Policy Gradient Theorem Using Emphatic Weightings
Ehsan Imani, Eric Graves, Martha White
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorit…
Learning Scheduling Algorithms for Data Processing Clusters
Hongzi Mao, Malte Schwarzkopf, Shaileshh Bojja Venkatakrishnan +2
Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore work…
Predicting Periodicity with Temporal Difference Learning
Kristopher De Asis, Brendan Bennett, Richard S. Sutton
Temporal difference (TD) learning is an important approach in reinforcement learning, as it combines ideas from dynamic programming and Monte Carlo methods in a way that allows for…
Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization
Bryan Wilder, Bistra Dilkina, Milind Tambe
Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typ…
A Unified Analysis of Stochastic Momentum Methods for Deep Learning
Yan Yan, Tianbao Yang, Zhe Li +2
Stochastic momentum methods have been widely adopted in training deep neural networks. However, their theoretical analysis of convergence of the training objective and the generali…
AXNet: ApproXimate computing using an end-to-end trainable neural network
Zhenghao Peng, Xuyang Chen, Chengwen Xu +4
Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approx…