Duke Computer Science at ICML 2020

June 24, 2020


Duke Comp Sci at ICML 2020Duke Computer Science students and professors will present nine (9) research papers at the ICML 2020 37th International Conference on Machine Learning July 12-18. Duke has an overall combined total of 22 paper presentations. A prestigious machine learning conference, this year ICML is virtual.

Duke Computer Science Research Papers at ICML 2020

  • Bandits for BMO Functions - Tianyu Wang (Duke), Cynthia Rudin (Duke)
  • Customizing ML Predictions for Online Algorithms - Keerti Anand (Duke), Rong Ge (Duke), Debmalya Panigrahi (Duke)
  • Generalized and Scalable Optimal Sparse Decision Trees - Jimmy Lin (Univ. of BC), Chudi Zhong (Duke), Diane Hu (Duke), Cynthia Rudin (Duke), Margo Seltzer (Univ. of BC)
  • High-dimensional Robust Mean Estimation via Gradient Descent - Yu Cheng (Univ. of Illinois at Chicago), Ilias Diakonikolas (Univ. of Wisconsin-Madison), Rong Ge (Duke), Mahdi Soltanolkotabi (Univ. of So. Cal.)
  • Influence Diagram Bandits - Tong Yu (CMU), Branislav Kveton (Google Research), Zheng Wen (DeepMind), Ruiyi Zhang (Duke), Ole J. Mengshoel (CMU)
  • Learning Opinions in Social Networks - Vincent Conitzer (Duke), Debmalya Panigrahi (Duke), Hanrui Zhang (Duke)
  • Learning the Valuations of a k-demand Agent - Hanrui Zhang (Duke), Vincent Conitzer (Duke)
  • Nearly Linear Row Sampling Algorithm for Quantile Regression - Yi Li (Nanyang Technological Univ.), Ruosong Wang (CMU), Lin Yang (UCLA), Hanrui Zhang (Duke)
  • Robust Pricing in Dynamic Mechanism Design - Yuan Deng (Duke), Sébastien Lahaie (Google), Vahab Mirrokni (Google Research)

Other Duke Papers

  • Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning - Tung-Che Liang (Duke), Zhanwei Zhong (Duke), Yaas Bigdeli (Duke), Tsung-Yi Ho (National Tsing Hua Univ.), Richard Fair (Duke), Krishnendu Chakrabarty (Duke)
  • CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods - Wei Zhang (Facebook), Thomas Panum (Aalborg Univ.), Somesh Jha (Univ. of WI, Madison), Prasad Chalasani (XaiPient), David Page (Duke)
  • CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information - Pengyu Cheng (Duke), Weituo Hao (Duke), Shuyang Dai (Duke), Jiachang Liu (Duke), Zhe Gan (Microsoft), Lawrence Carin (Duke)
  • The Cost-free Nature of Optimally Tuning Tikhonov Regularizers and Other Ordered Smoothers - Pierre Bellec (Rutgers), Dana Yang (Duke)
  • Fiedler Regularization: Learning Neural Networks with Graph Sparsity - Edric Tam (Duke), David Dunson (Duke)
  • Graph Optimal Transport for Cross-Domain Alignment - Liqun Chen (Duke), Zhe Gan (Microsoft), Yu Cheng (Microsoft), Linjie Li (Microsoft), Lawrence Carin (Duke), Jingjing Liu (Microsoft)
  • Learning Autoencoders with Relational Regularization - Hongteng Xu (InfiniaML, Inc.), Dixin Luo (Duke), Ricardo Henao (Duke), Svati Shah (Duke), Lawrence Carin (Duke)
  • A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth - Yiping Lu (Stanford), Chao Ma (Princeton), Yulong Lu (Duke), Jianfeng Lu (Duke), Lexing Ying (Stanford)
  • Minimax Pareto Fairness: A Multi Objective Perspective - Martin Bertran (Duke), Natalia Martinez (Duke), Guillermo Sapiro (Duke)
  • On Leveraging Pretrained GANs for Limited-Data Generation - Miaoyun Zhao (Duke), Yulai Cong (Duke), Lawrence Carin (Duke)
  • PENNI: Pruned Kernel Sharing for Efficient CNN Inference - Shiyu Li (Duke), Edward Hanson (Duke), Hai Li (Duke), Yiran Chen (Duke)
  • Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory - Zhou Fan (Yale), Cheng Mao (GA Institute of Technology), Yihong Wu (Yale), Jiaming Xu (Duke)
  • Variance Reduction and Quasi-Newton for Particle-Based Variational Inference - Michael Zhu (Stanford), Chang Liu (Microsoft Research), Jun Zhu (Tsinghua Univ.)