Europe
Deep Generative Models for Distribution-Preserving Lossy Compression
Michael Tschannen, Eirikur Agustsson, Mario Lucic
Neural Information Processing Systems http://nips.cc/
a7471fdc77b3435276507cc8f2dc2569-Paper.pdf
We propose simple robust variants of two notions that havebeen considered inrecent literature: (in)fidelity,and sensitivity.
Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
Andrea Zanette, Mykel J. Kochenderfer, Emma Brunskill
Inparticular,well knownbounds foronline learningscale as a function of the gap between the expected reward of a particular action and the optimalaction [ABF02] and also on the variance ofthe rewards [AMS09].
Towards Deep Conversational Recommendations
Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, Chris Pal
Neural Information Processing Systems http://nips.cc/
Inequity aversion improves cooperation in intertemporal social dilemmas
Edward Hughes, Joel Z. Leibo, Matthew Phillips, Karl Tuyls, Edgar Dueรฑez-Guzman, Antonio Garcรญa Castaรฑeda, Iain Dunning, Tina Zhu, Kevin McKee, Raphael Koster, Heather Roff, Thore Graepel
Neural Information Processing Systems http://nips.cc/
Generalization Bounds in the Predict-then-Optimize Framework
Othman El Balghiti, Adam Elmachtoub, Paul Grigas, Ambuj Tewari
Neural Information Processing Systems http://nips.cc/
Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation
Shift-and-invert preconditioning, as a classic acceleration technique for the leading eigenvector computation, has received much attention again recently, owing to fast least-squares solvers for efficiently approximating matrix inversions in power iterations.
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection
Taylor Mordan, Nicolas THOME, Gilles Henaff, Matthieu Cord
Extensiveexperiments on NYUv2 dataset (object detection with scene classification, depth prediction, and surface normal estimation as auxiliary tasks) validate the relevance of the approach and its superiority to flat MTL approaches.