ICLR

Meta-Learning for Semi-Supervised Few-Shot Classification

Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel

Comments Published as a conference paper at ICLR 2018. 15 pages

Semi-parametric Topological Memory for Navigation

Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun

Comments Published at International Conference on Learning Representations (ICLR) 2018. Project website at https://sites.google.com/view/SPTM

Interpretable Counting for Visual Question Answering

Alexander Trott, Caiming Xiong, Richard Socher

Comments ICLR 2018

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

Journal ref Sixth International Conference on Learning Representations (ICLR), 2018

MaskGAN: Better Text Generation via Filling in the______

William Fedus, Ian Goodfellow, Andrew M. Dai

Comments 16 pages, ICLR 2018

Mitigating Adversarial Effects Through Randomization

Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille

Comments To appear in ICLR 2018, code available at https://github.com/cihangxie/NIPS2017_adv_challenge_defense

Memory-based Parameter Adaptation

Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell

Comments Published as a conference paper at ICLR 2018

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions

Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber

Comments Accepted to ICLR 2018

On the scaling of polynomial features for representation matching

Siddhartha Brahma

Comments 4 pages, Submitted to ICLR 2018 workshop

SufiSent - Universal Sentence Representations Using Suffix Encodings

Siddhartha Brahma

Comments 4 pages, Submitted to ICLR 2018 workshop

Learning from Between-class Examples for Deep Sound Recognition

Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada

Comments 13 pages, 6 figures, published as a conference paper at ICLR 2018

When is a Convolutional Filter Easy To Learn?

Simon S. Du, Jason D. Lee, Yuandong Tian

Comments Published as a conference paper at ICLR 2018

Understanding Deep Neural Networks with Rectified Linear Units

Raman Arora, Amitabh Basu, Poorya Mianjy, Anirbit Mukherjee

Comments The poly(data) exact training algorithm has been improved to now be applicable to any single hidden layer R^n-> R ReLU DNN and there is a cleaner pseudocode for it given on page 8. Also now on page 7 there is a more precise description about when and how the Zonotope construction improves on the Theorem 4 of this paper, arXiv:1402.1869

Journal ref ICLR 2028

Not-So-Random Features

Brian Bullins, Cyril Zhang, Yi Zhang

Comments Published as a conference paper at ICLR 2018

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen

Comments Final ICLR 2018 version

Detecting Statistical Interactions from Neural Network Weights

Michael Tsang, Dehua Cheng, Yan Liu

Comments Published in ICLR 2018

Scalable Private Learning with PATE

Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson

Comments Published as a conference paper at ICLR 2018

Unsupervised Neural Machine Translation

Mikel Artetxe, Gorka Labaka, Eneko Agirre, Kyunghyun Cho

Comments Published as a conference paper at ICLR 2018

Understanding image motion with group representations

Andrew Jaegle, Stephen Phillips, Daphne Ippolito, Kostas Daniilidis

Comments Published as a conference paper at ICLR 2018; 14 pages, including references and supplement

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling

Carlos Riquelme, George Tucker, Jasper Snoek

Comments Sixth International Conference on Learning Representations, ICLR 2018

Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration

Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, Percy Liang

Comments International Conference on Learning Representations (ICLR), 2018

Syntax-Directed Variational Autoencoder for Structured Data

Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song

Comments to appear in ICLR 2018

Training wide residual networks for deployment using a single bit for each weight

Mark D. McDonnell

Comments Published as a conference paper at ICLR 2018

Journal ref ICLR 2018 - International Conference on Learning Representations, Apr 2018, Vancouver, Canada. 2018

FearNet: Brain-Inspired Model for Incremental Learning

Ronald Kemker, Christopher Kanan

Comments To appear in ICLR 2018

On the Discrimination-Generalization Tradeoff in GANs

Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He

Comments ICLR 2018

Large-Scale Optimal Transport and Mapping Estimation

Vivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary, Nicolas Courty, Antoine Rolet, Mathieu Blondel

Comments 15 pages, 4 figures. To appear in the Proceedings of the International Conference on Learning Representations (ICLR) 2018

Synthetic and Natural Noise Both Break Neural Machine Translation

Yonatan Belinkov, Yonatan Bisk

Comments ICLR 2018 camera-ready

Don't Decay the Learning Rate, Increase the Batch Size

Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

Comments 11 pages, 8 figures. Published as a conference paper at ICLR 2018

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation

Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud

Comments Published at ICLR 2018

Generating Natural Adversarial Examples

Zhengli Zhao, Dheeru Dua, Sameer Singh

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR) 2018