ICLR

Improved memory in recurrent neural networks with sequential non-normal dynamics

A. Emin Orhan, Xaq Pitkow

Comments Published as a conference paper at ICLR 2020

Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs

Aditya Paliwal, Felix Gimeno, Vinod Nair, Yujia Li, Miles Lubin, Pushmeet Kohli, Oriol Vinyals

Comments Accepted to ICLR 2020 https://openreview.net/forum?id=rkxDoJBYPB

Robust and interpretable blind image denoising via bias-free convolutional neural networks

Sreyas Mohan, Zahra Kadkhodaie, Eero P. Simoncelli, Carlos Fernandez-Granda

Comments Published as conference paper in ICLR 2020

Implementing Inductive bias for different navigation tasks through diverse RNN attractors

Tie Xu, Omri Barak

Comments Main text: 11 pages, 5 figures. Supplementary: 16 pages, 14 figures, 3 tables. Accepted as a conference paper for ICLR 2020

Learning to Learn by Zeroth-Order Oracle

Yangjun Ruan, Yuanhao Xiong, Sashank Reddi, Sanjiv Kumar, Cho-Jui Hsieh

Comments Published as a conference paper at ICLR 2020

On Identifiability in Transformers

Gino Brunner, Yang Liu, Damián Pascual, Oliver Richter, Massimiliano Ciaramita, Roger Wattenhofer

Comments Published as a conference paper at ICLR 2020

DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling

Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari, Hannaneh Hajishirzi

Comments Accepted at ICLR 2020

Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks

Joonyoung Yi, Juhyuk Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang

Comments 27 pages

Journal ref Nucl.Phys.Proc.Suppl. 109 (2002) 3-9 Nucl.Phys.Proc.Suppl. 109 (2002) 3-9 Nucl.Phys.Proc.Suppl. 109 (2002) 3-9 Proceedings of International Conference on Learning Representations (ICLR) 2020

Low-dimensional statistical manifold embedding of directed graphs

Thorben Funke, Tian Guo, Alen Lancic, Nino Antulov-Fantulin

Comments camera ready version ICLR 2020

Journal ref ICLR 2020

Generative Models for Effective ML on Private, Decentralized Datasets

Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Aguera y Arcas

Comments 26 pages, 8 figures. Camera-ready ICLR 2020 version

Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform

Jun Li, Li Fuxin, Sinisa Todorovic

Comments ICLR 2020 conference paper

Are adversarial examples inevitable?

Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein

Journal ref International Conference on Learning Representations, 2019. https://openreview.net/forum?id=r1lWUoA9FQ

Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction

Taeuk Kim, Jihun Choi, Daniel Edmiston, Sang-goo Lee

Comments ICLR 2020

Gap Aware Mitigation of Gradient Staleness

Saar Barkai, Ido Hakimi, Assaf Schuster

Comments Published as a conference paper at ICLR 2020

Robust Local Features for Improving the Generalization of Adversarial Training

Chuanbiao Song, Kun He, Jiadong Lin, Liwei Wang, John E. Hopcroft

Comments accepted by ICLR 2020

Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks

Jiadong Lin, Chuanbiao Song, Kun He, Liwei Wang, John E. Hopcroft

Comments ICLR 2020

Duration-of-Stay Storage Assignment under Uncertainty

Michael Lingzhi Li, Elliott Wolf, Daniel Wintz

Comments 15 pages, 4 figures. Accepted at ICLR 2020

PCMC-Net: Feature-based Pairwise Choice Markov Chains

Alix Lhéritier

Comments Final version to be published in ICLR 2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Yixiao Ge, Dapeng Chen, Hongsheng Li

Comments Accepted in International Conference on Learning Representations (ICLR 2020)

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

Daniel Stoller, Sebastian Ewert, Simon Dixon

Comments 10 pages plus 14 pages appendix. Accepted at the International Conference on Learning Representations (ICLR) 2020. Camera-ready submission. Implementation available at https://github.com/f90/FactorGAN

MEMO: A Deep Network for Flexible Combination of Episodic Memories

Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell

Comments 9 pages, 2 figures, 3 tables, to be published as a conference paper at ICLR 2020

Jacobian Adversarially Regularized Networks for Robustness

Alvin Chan, Yi Tay, Yew Soon Ong, Jie Fu

Comments ICLR 2020 Camera Ready

Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds

Lukas Prantl, Nuttapong Chentanez, Stefan Jeschke, Nils Thuerey

Comments Further information and videos at https://ge.in.tum.de/publications/2020-iclr-prantl/

Controlling generative models with continuous factors of variations

Antoine Plumerault, Hervé Le Borgne, Céline Hudelot

Comments Accepted as a poster presentation at the International Conference for Learning Representations (ICLR), 2020

Using Simulated Data to Generate Images of Climate Change

Gautier Cosne, Adrien Juraver, Mélisande Teng, Victor Schmidt, Vahe Vardanyan, Alexandra Luccioni, Yoshua Bengio

Comments Proceeding ML-IRL workshop at ICLR 2020

Understanding and Robustifying Differentiable Architecture Search

Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, Frank Hutter

Comments In: International Conference on Learning Representations (ICLR 2020); 28 pages, 30 figures

What graph neural networks cannot learn: depth vs width

Andreas Loukas

Comments 17 pages, 10 figures. International Conference on Learning Representations (ICLR), 2020

Variance Reduction with Sparse Gradients

Melih Elibol, Lihua Lei, Michael I. Jordan

Comments ICLR 2020

Deep Graph Matching Consensus

Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege

Comments Published as a conference paper at ICLR 2020

Fast Task Inference with Variational Intrinsic Successor Features

Steven Hansen, Will Dabney, Andre Barreto, Tom Van de Wiele, David Warde-Farley, Volodymyr Mnih

Comments Accepted for publication at ICLR 2020