ICLR

Deep Frank-Wolfe For Neural Network Optimization

Leonard Berrada, Andrew Zisserman, M. Pawan Kumar

Comments Published as a conference paper at ICLR 2019, last version fixing an inaccuracy (details in appendix A.5, Proposition 2)

Journal ref International Conference on Learning Representations 2019

Effective and Efficient Vote Attack on Capsule Networks

Jindong Gu, Baoyuan Wu, Volker Tresp

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

Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System

Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu

Comments Published as a conference paper at ICLR 2021

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers

Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi

Comments Accepted to ICLR 2021

Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels

Binxin Ru, Xingchen Wan, Xiaowen Dong, Michael Osborne

Comments ICLR 2021. 9 pages, 5 figures, 1 table (23 pages, 14 figures and 3 tables including references and appendices)

Unbiased Teacher for Semi-Supervised Object Detection

Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda

Comments Accepted to ICLR 2021; Code is available at https://github.com/facebookresearch/unbiased-teacher

DINO: A Conditional Energy-Based GAN for Domain Translation

Konstantinos Vougioukas, Stavros Petridis, Maja Pantic

Comments Accepted to ICLR 2021

On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers

Kenji Kawaguchi

Comments ICLR 2021. Selected for ICLR Spotlight (top 6% submissions)

Differentially Private Learning Needs Better Features (or Much More Data)

Florian Tramèr, Dan Boneh

Comments ICLR 2021. Code available at https://github.com/ftramer/Handcrafted-DP

Fast Geometric Projections for Local Robustness Certification

Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina Păsăreanu

Comments Appearing in ICLR 2021

Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters

Aston Zhang, Yi Tay, Shuai Zhang, Alvin Chan, Anh Tuan Luu, Siu Cheung Hui, Jie Fu

Comments Published as a conference paper at the 9th International Conference on Learning Representations (ICLR 2021)

End-to-End Egospheric Spatial Memory

Daniel Lenton, Stephen James, Ronald Clark, Andrew J. Davison

Comments Conference paper at ICLR 2021. Implementation: https://github.com/ivy-dl/memory Project page: https://djl11.github.io/ESM/

Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry

Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang

Comments To appear in ICLR 2021

Zero-shot Synthesis with Group-Supervised Learning

Yunhao Ge, Sami Abu-El-Haija, Gan Xin, Laurent Itti

Comments Published at ICLR 2021 (16 pages including appendix)

Meta Back-translation

Hieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig

Comments Accepted to ICLR 2021

ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations

Rishabh Tiwari, Udbhav Bamba, Arnav Chavan, Deepak K. Gupta

Comments Accepted at ICLR 2021 Conference

Efficient Continual Learning with Modular Networks and Task-Driven Priors

Tom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato

Comments Accepted as a conference paper at ICLR 2021

DeLighT: Deep and Light-weight Transformer

Sachin Mehta, Marjan Ghazvininejad, Srinivasan Iyer, Luke Zettlemoyer, Hannaneh Hajishirzi

Comments Accepted at ICLR 2021

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau

Comments Accepted at the 9th International Conference on Learning Representations. 22 pages, 14 figures

Learning to Set Waypoints for Audio-Visual Navigation

Changan Chen, Sagnik Majumder, Ziad Al-Halah, Ruohan Gao, Santhosh Kumar Ramakrishnan, Kristen Grauman

Comments Accepted to ICLR 2021

Influence Functions in Deep Learning Are Fragile

Samyadeep Basu, Philip Pope, Soheil Feizi

Comments ICLR 2021

Negative Data Augmentation

Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon

Comments Accepted at ICLR 2021

Score-Based Generative Modeling through Stochastic Differential Equations

Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole

Comments ICLR 2021 (Oral)

Open Question Answering over Tables and Text

Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Wang, William W. Cohen

Comments Accepted to ICLR 2021. Main paper has 9 pages

A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention

Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal

Comments ICLR 2021

Saliency is a Possible Red Herring When Diagnosing Poor Generalization

Joseph D. Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen

Comments 25 pages, 27 figures, 5 tables, code in paper (https://github.com/josephdviviano/saliency-red-herring). Published at International Conference on Learning Representations (ICLR) 2021. Previously titled "Underwhelming Generalization Improvements from Controlling Feature Attribution"

Learning Manifold Patch-Based Representations of Man-Made Shapes

Dmitriy Smirnov, Mikhail Bessmeltsev, Justin Solomon

Comments Accepted to ICLR 2021

Spatio-Temporal Graph Scattering Transform

Chao Pan, Siheng Chen, Antonio Ortega

Comments 18 pages, ICLR 2021

When Do Curricula Work?

Xiaoxia Wu, Ethan Dyer, Behnam Neyshabur

Comments ICLR 2021

Adversarially Guided Actor-Critic

Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist

Comments Accepted at ICLR 2021