ICLR

Deep Learning Hamiltonian Monte Carlo

Sam Foreman, Xiao-Yong Jin, James C. Osborn

Comments 8 pages, 7 figures, Published as a workshop paper at ICLR 2021 SimDL Workshop

Energy-Based Anomaly Detection and Localization

Ergin Utku Genc, Nilesh Ahuja, Ibrahima J Ndiour, Omesh Tickoo

Comments 9 pages, 3 figures, as submitted to EBM ICLR 2021 workshop

Network Pruning That Matters: A Case Study on Retraining Variants

Duong H. Le, Binh-Son Hua

Comments Accepted at ICLR 2021 (Poster)

A Discriminative Gaussian Mixture Model with Sparsity

Hideaki Hayashi, Seiichi Uchida

Comments Published as a conference paper at ICLR 2021

Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments

Martin Schuessler, Philipp Weiß, Leon Sixt

Comments 6 pages, 3 figures, presented at the ICLR 2021 RAI workshop

A Distributional Approach to Controlled Text Generation

Muhammad Khalifa, Hady Elsahar, Marc Dymetman

Comments ICLR 2021 camera-ready version

Byzantine-Robust and Privacy-Preserving Framework for FedML

Hanieh Hashemi, Yongqin Wang, Chuan Guo, Murali Annavaram

Journal ref Security and Safety in Machine Learning Systems Workshop in ICLR 2021

Iterated learning for emergent systematicity in VQA

Ankit Vani, Max Schwarzer, Yuchen Lu, Eeshan Dhekane, Aaron Courville

Comments Published as a conference paper at ICLR 2021. 9 pages main, 21 pages total including references and appendix

Journal ref 9th International Conference on Learning Representations (ICLR 2021)

Deep Networks and the Multiple Manifold Problem

Sam Buchanan, Dar Gilboa, John Wright

Comments ICLR 2021

MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

Tsung Wei Tsai, Chongxuan Li, Jun Zhu

Comments International Conference on Learning Representations (ICLR) 2021

Multigrid Solver With Super-Resolved Interpolation

Francisco Holguin, GS Sidharth, Gavin Portwood

Comments Accepted at ICLR 2021 SimDL workshop

COVID-19 Detection from Chest X-ray Images using Imprinted Weights Approach

Jianxing Zhang, Pengcheng Xi, Ashkan Ebadi, Hilda Azimi, Stephane Tremblay, Alexander Wong

Comments Accepted to ICLR 2021 Workshop: Machine Learning for Preventing and Combating Pandemics

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum

Comments https://sites.google.com/view/opal-iclr

How Does Supernet Help in Neural Architecture Search?

Yuge Zhang, Quanlu Zhang, Yaming Yang

Comments Accepted by 2nd Workshop on Neural Architecture Search at ICLR 2021

Reinforcement Learning with Random Delays

Simon Ramstedt, Yann Bouteiller, Giovanni Beltrame, Christopher Pal, Jonathan Binas

Comments ICLR 2021

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

Cristina Guzman, Daphna Keidar, Tristan Meynier, Andreas Opedal, Niklas Stoehr

Comments Accepted at the 9th International Conference on Learning Representations (ICLR 2021), Workshop on Geometrical and Topological Representation Learning

Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?

Zhiyuan Li, Yi Zhang, Sanjeev Arora

Comments 24 pages, 1 figure; Accepted by ICLR 2021

Learned transform compression with optimized entropy encoding

Magda Gregorová, Marc Desaules, Alexandros Kalousis

Comments Published as a workshop paper at ICLR 2021 neural compression workshop

Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning

Haibo Yang, Minghong Fang, Jia Liu

Comments Published as a conference paper at ICLR 2021, fixed errors in theorem 2

Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks

Thomas Bird, Friso H. Kingma, David Barber

Comments Accepted to ICLR 2021

Privacy and Integrity Preserving Training Using Trusted Hardware

Hanieh Hashemi, Yongqin Wang, Murali Annavaram

Journal ref Distributed and Private Machine Learning ICLR 2021 Workshop

Deep Convolution for Irregularly Sampled Temporal Point Clouds

Erich Merrill, Stefan Lee, Li Fuxin, Thomas G. Dietterich, Alan Fern

Comments 12 pages, submitted to ICLR 2021

Bermuda Triangles: GNNs Fail to Detect Simple Topological Structures

Arseny Tolmachev, Akira Sakai, Masaru Todoriki, Koji Maruhashi

Comments ICLR 2021 GTRL Poster Presentation: https://openreview.net/forum?id=Vz_Nl9MSQnu

Submodular Mutual Information for Targeted Data Subset Selection

Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer

Comments Accepted to ICLR 2021 S2D-OLAD Workshop; https://s2d-olad.github.io/. arXiv admin note: substantial text overlap with arXiv:2103.00128

Improved and Efficient Text Adversarial Attacks using Target Information

Mahmoud Hossam, Trung Le, He Zhao, Viet Huynh, Dinh Phung

Comments Accepted in the International Conference on Learning Representations (ICLR) workshop on Robust and Reliable Machine Learning in the Real World (RobustML)

Failing Conceptually: Concept-Based Explanations of Dataset Shift

Maleakhi A. Wijaya, Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik

Comments ICLR 2021 Workshop (RobustML), 16 pages, 14 figures; typos corrected

Learning What To Do by Simulating the Past

David Lindner, Rohin Shah, Pieter Abbeel, Anca Dragan

Comments Presented at ICLR 2021

EEC: Learning to Encode and Regenerate Images for Continual Learning

Ali Ayub, Alan R. Wagner

Comments Added link to the code in the paper. A preliminary version of this work was presented at ICML 2020 Workshop on Lifelong Machine Learning: arXiv:2007.06637

Journal ref International Conference on Learning Representations (ICLR) 2021

Latent Skill Planning for Exploration and Transfer

Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti

Comments First two authors contributed equally. Published as a conference paper in ICLR 2021

Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization

Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel

Comments Published at ICLR 2021. Joint first and last authors. Code is available at https://bethgelab.github.io/testing_visualizations/