Bayesian Optimization of Risk Measures
By Sait Cakmak (Georgia Tech); Rahul Austdillo (Cornell University); Peter Frazier (Cornell University); Enlu Zhou (Georgia Tech)
Posterior Re-calibration for Imbalanced Datasets
By Junjiao Tian (Georgia Tech); Yen-Cheng Liu (Georgia Tech); Nathaniel Glaser (Georgia Tech); Yen-Chang Hsu (Georgia Tech); Zsolt Kira (Georgia Tech)
Generative causal explanations of black-box classifiers
By Matt O’Shaughnessy (Georgia Tech); Greg Canal (Georgia Tech); Marissa Connor (Georgia Tech); Mark Davenport (Georgia Tech); Christopher Rozell (Georgia Tech)
Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes
By Zaiwei Chen (Georgia Tech); Siva Theja Maguluri (Georgia Tech); Sanjay Shakkottai (The University of Texas at Austin); Karthikeyan Shanmugam (IBM Research NY)
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
By Minshuo Chen (Georgia Tech); Yu Bai (Salesforce Research); Jason Lee (Princeton University); Tuo Zhao (Georgia Tech); Huan Wang (Salesforce Research); Caiming Xiong (Salesforce Research); Richard Socher (Salesforce Research)
Walking in the Shadow: A New Perspective on Feasible Descent Directions
By Hassan Mortagy (Georgia Tech); Swati Gupta (Georgia Tech); Sebastian Pokutta (Zuse Institute Berlin)
A Robust Functional EM Algorithm for Incomplete Panel Count Data
By Alexander Moreno (Georgia Tech); Zhenke Wu (University of Michigan); Jamie Yap (University of Michigan); Cho Lam (University of Utah); David Wetter (University of Utah); Inbal Nahum-Shani (University of Michigan); Walter Dempsey (University of Michigan); James M. Rehg (Georgia Tech)
Estimating Mass Distribution of Articulated Objects Using Non-Prehensile Manipulation
By K. Niranjan Kumar (Georgia Tech); Irfan Essa (Georgia Tech); Sehoon Ha (Georgia Tech); C. Karen Liu (Stanford University)
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
By Amir Rahimi (ANU, ACRV); Amirreza Shaban (Georgia Tech); Ching-An Cheng (Microsoft Research); Byron Boots (University of Washington); Richard Hartley (Google Research and ANU, ACRV)