Deep Learning
Doubly Stochastic Variational Inference for Deep Gaussian Processes
Hugh Salimbeni, Marc Deisenroth
Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice.
Mean Field Residual Networks: On the Edge of Chaos Greg Y ang
Work done while at Harvard University 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. These works have focused on vanilla (fully connected) feedforward networks.
The Marginal Value of Adaptive Gradient Methods in Machine Learning
Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nati Srebro, Benjamin Recht
Examples include AdaGrad, RMSProp, and Adam.
Toward Multimodal Image-to-Image Translation
Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A. Efros, Oliver Wang, Eli Shechtman
Neural Information Processing Systems http://nips.cc/
Positive-Unlabeled Learning with Non-Negative Risk Estimator
Ryuichi Kiryo, Gang Niu, Marthinus C. du Plessis, Masashi Sugiyama
Neural Information Processing Systems http://nips.cc/
Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis
Jian Zhao, Lin Xiong, Panasonic Karlekar Jayashree, Jianshu Li, Fang Zhao, Zhecan Wang, Panasonic Sugiri Pranata, Panasonic Shengmei Shen, Shuicheng Yan, Jiashi Feng
The dual agents are specifically designed for distinguishing real v.s.
Training Deep Networks without Learning Rates Through Coin Betting
Francesco Orabona, Tatiana Tommasi
Neural Information Processing Systems http://nips.cc/
Stabilizing Training of Generative Adversarial Networks through Regularization
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann
In what follows, we will take Eq.
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
Marco Fraccaro, Simon Kamronn, Ulrich Paquet, Ole Winther
From the earliest stages of childhood, humans learn to represent high-dimensional sensory input to make temporal predictions. From the visual image of a moving tennis ball, we can imagine its trajectory, and prepare ourselves in advance to catch it.
Neural Discrete Representation Learning
Aaron van den Oord, Oriol Vinyals, koray kavukcuoglu
Learning useful representations without supervision remains a key challenge in machine learning.