ICLR

Gradient Projection Memory for Continual Learning

Gobinda Saha, Isha Garg, Kaushik Roy

Comments Accepted for Oral Presentation at ICLR 2021 https://openreview.net/forum?id=3AOj0RCNC2

Journal ref International Conference on Learning Representations (ICLR), 2021

Training GANs with Stronger Augmentations via Contrastive Discriminator

Jongheon Jeong, Jinwoo Shin

Comments 23 pages; ICLR 2021

Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning

Siyang Yuan, Pengyu Cheng, Ruiyi Zhang, Weituo Hao, Zhe Gan, Lawrence Carin

Comments To appear in ICLR 2021

Meta-learning with negative learning rates

Alberto Bernacchia

Comments Accepted at ICLR 2021

Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models

Justin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt

Comments Published as a conference paper at ICLR 2021 (Poster)

On the role of planning in model-based deep reinforcement learning

Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber

Comments Published at ICLR 2021

MixKD: Towards Efficient Distillation of Large-scale Language Models

Kevin J Liang, Weituo Hao, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin

Comments ICLR 2021 Camera Ready

Self-training for Few-shot Transfer Across Extreme Task Differences

Cheng Perng Phoo, Bharath Hariharan

Comments Published as a conference paper at ICLR 2021(oral)

Sparse Quantized Spectral Clustering

Zhenyu Liao, Romain Couillet, Michael W. Mahoney

Journal ref International Conference on Learning Representations (ICLR 2021), https://openreview.net/forum?id=pBqLS-7KYAF

Integrating Categorical Semantics into Unsupervised Domain Translation

Samuel Lavoie, Faruk Ahmed, Aaron Courville

Comments 22 pages. In submission to the International Conference on Learning Representation (ICLR) 2021

EigenGame: PCA as a Nash Equilibrium

Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel

Comments Published as a conference paper at International Conference on Learning Representations (ICLR) 2021

Sample-Efficient Automated Deep Reinforcement Learning

Jörg K. H. Franke, Gregor Köhler, André Biedenkapp, Frank Hutter

Comments In Proceedings of the International Conference on Learning Representations (ICLR 2021), 2021

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

David Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan Paiton

Comments ICLR 2021. Code is available at https://github.com/bethgelab/slow_disentanglement. The first three authors, as well as the last two authors, contributed equally

Lifelong Learning of Compositional Structures

Jorge A. Mendez, Eric Eaton

Comments ICLR-2021. Code: https://github.com/Lifelong-ML/Mendez2020Compositional.git

Tilted Empirical Risk Minimization

Tian Li, Ahmad Beirami, Maziar Sanjabi, Virginia Smith

Comments Accepted by ICLR 2021

Sliced Kernelized Stein Discrepancy

Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato

Comments Published at ICLR 2021

Hyperbolic Neural Networks++

Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada

Comments The Ninth International Conference on Learning Representations (ICLR 2021)

Primal Wasserstein Imitation Learning

Robert Dadashi, Léonard Hussenot, Matthieu Geist, Olivier Pietquin

Comments Published in International Conference on Learning Representations (ICLR 2021)

End-to-End Adversarial Text-to-Speech

Jeff Donahue, Sander Dieleman, Mikołaj Bińkowski, Erich Elsen, Karen Simonyan

Comments 23 pages. In proceedings of ICLR 2021

Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning

Namyeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien

Comments Appears in: Proceedings of the Ninth International Conference on Learning Representations (ICLR 2021). 20 pages

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling

Đorđe Miladinović, Aleksandar Stanić, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann

Journal ref International Conference on Learning Representations (2021);

Revisiting Dynamic Convolution via Matrix Decomposition

Yunsheng Li, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Ye Yu, Lu Yuan, Zicheng Liu, Mei Chen, Nuno Vasconcelos

Comments Accepted by ICLR 2021

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective

Wuyang Chen, Xinyu Gong, Zhangyang Wang

Comments accepted as ICLR 2021 poster

Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers

Kaidi Xu, Huan Zhang, Shiqi Wang, Yihan Wang, Suman Jana, Xue Lin, Cho-Jui Hsieh

Comments Accepted by ICLR 2021

Learning Value Functions in Deep Policy Gradients using Residual Variance

Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux

Comments Accepted at ICLR 2021

DrNAS: Dirichlet Neural Architecture Search

Xiangning Chen, Ruochen Wang, Minhao Cheng, Xiaocheng Tang, Cho-Jui Hsieh

Comments ICLR 2021, code is available at https://github.com/xiangning-chen/DrNAS

Decoupling Global and Local Representations via Invertible Generative Flows

Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

Comments Camera-ready at ICLR 2021. 23 pages (plus appendix), 16 figures, 5 tables. Due to arxiv size constraints, this version is using downscaled images. Please download the full-resolution version from https://vixra.org/abs/2004.0222

Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online

Yangchen Pan, Kirby Banman, Martha White

Comments ICLR 2021

Mutual Information State Intrinsic Control

Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

Comments Published in International Conference on Learning Representations (ICLR 2021) as Spotlight (top 5%), Link: https://openreview.net/forum?id=OthEq8I5v1. arXiv admin note: text overlap with arXiv:2002.01963

Can a Fruit Fly Learn Word Embeddings?

Yuchen Liang, Chaitanya K. Ryali, Benjamin Hoover, Leopold Grinberg, Saket Navlakha, Mohammed J. Zaki, Dmitry Krotov

Comments Accepted for publication at ICLR 2021