作者：我爱机器学习
原文链接：ICML历年Best Papers
| ICML (Machine Learning)(1999-2016) | |||
| 2016 | Dueling Network Architectures for Deep Reinforcement Learning | Ziyu Wang | Google Inc. |
| Pixel Recurrent Neural Networks | Aaron van den Oord | Google DeepMind | |
| Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling | Christopher De Sa | Stanford | |
| 2015 | A Nearly-Linear Time Framework for Graph-Structured Sparsity | Chinmay Hegde | Massachusetts Institute of Technology |
| Optimal and Adaptive Algorithms for Online Boosting | Alina Beygelzimer | Yahoo! Research | |
| 2014 | Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis | Jian Tang | Peking University |
| 2013 | Vanishing Component Analysis | Roi Livni | The Hebrew University of Jerusalum |
| Fast Semidifferential-based Submodular Function Optimization | Rishabh Iyer | University of Washington | |
| 2012 | Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring | Sungjin Ahn | University of California Irvine |
| 2011 | Computational Rationalization: The Inverse Equilibrium Problem | Kevin Waugh | Carnegie Mellon University |
| 2010 | Hilbert Space Embeddings of Hidden Markov Models | Le Song | Carnegie Mellon University |
| 2009 | Structure preserving embedding | Blake Shaw | Columbia University |
| 2008 | SVM Optimization: Inverse Dependence on Training Set Size | Shai Shalev-Shwartz | Toyota Technological Institute at Chicago |
| 2007 | Information-theoretic metric learning | Jason V. Davis | University of Texas at Austin |
| 2006 | Trading convexity for scalability | Ronan Collobert | NEC Labs America |
| 2005 | A support vector method for multivariate performance measures | Thorsten Joachims | Cornell University |
| 1999 | Least-Squares Temporal Difference Learning | Justin A. Boyan | NASA Ames Research Center |