ICLR

What can human minimal videos tell us about dynamic recognition models?

Guy Ben-Yosef, Gabriel Kreiman, Shimon Ullman

Comments Published as a workshop paper at Bridging AI and Cognitive Science (ICLR 2020). Extended paper was published at Cognition

Forecasting COVID-19 Counts At A Single Hospital: A Hierarchical Bayesian Approach

Alexandra Hope Lee, Panagiotis Lymperopoulos, Joshua T. Cohen, John B. Wong, Michael C. Hughes

Comments In ICLR 2021 Workshop on Machine Learning for Preventing and Combating Pandemics

In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning

Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, Mubarak Shah

Comments ICLR 2021

Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures

Pedro Hermosilla, Marco Schäfer, Matěj Lang, Gloria Fackelmann, Pere Pau Vázquez, Barbora Kozlíková, Michael Krone, Tobias Ritschel, Timo Ropinski

Comments International Conference on Learning Representations (ICLR) 2021

CPR: Classifier-Projection Regularization for Continual Learning

Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio P. Calmon, Taesup Moon

Comments ICLR 2021 camera ready version

The Intrinsic Dimension of Images and Its Impact on Learning

Phillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein

Comments To appear at ICLR 2021 (spotlight), 17 pages with appendix, 15 figures

In Defense of the Paper

Owen Lockwood

Comments Accepted (oral) to Rethinking ML Papers - ICLR 2021 Workshop

Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

Zengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, Chuchu Fan

Comments Published at ICLR 2021

Predicting the Binding of SARS-CoV-2 Peptides to the Major Histocompatibility Complex with Recurrent Neural Networks

Johanna Vielhaben, Markus Wenzel, Eva Weicken, Nils Strodthoff

Comments Accepted at ICLR 2021 Workshop: Machine Learning for Preventing and Combating Pandemics; code available at https://github.com/nstrodt/USMPep

Probing artificial neural networks: insights from neuroscience

Anna A. Ivanova, John Hewitt, Noga Zaslavsky

Comments ICLR 2021 Workshop: How Can Findings About The Brain Improve AI Systems?

Orthogonalizing Convolutional Layers with the Cayley Transform

Asher Trockman, J. Zico Kolter

Comments To appear in ICLR 2021

Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations

César Quilodrán-Casas, Rossella Arcucci, Laetitia Mottet, Yike Guo, Christopher Pain

Comments 8 pages; 3 figures; Published as a workshop paper at ICLR 2021 SimDL Workshop. arXiv admin note: text overlap with arXiv:2101.01568

SEED: Self-supervised Distillation For Visual Representation

Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu

Comments Accepted as a conference paper at ICLR 2021

RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers

Saeid Asgari Taghanaki, Jieliang Luo, Ran Zhang, Ye Wang, Pradeep Kumar Jayaraman, Krishna Murthy Jatavallabhula

Comments Published at the Robust and Reliable Machine Learning in the Real World Workshop, ICLR 2021

Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspective

Linhai Ma, Liang Liang

Comments This paper is accepted at ICLR 2020 workshop on Artificial Intelligence for Affordable Healthcare. 14 pages, 7 figures

Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learning

Joonyoung Yi, Buru Chang

Comments ICLR 2021 Workshop (PML4DC), 8 pages, 2 figures

ANEA: Distant Supervision for Low-Resource Named Entity Recognition

Michael A. Hedderich, Lukas Lange, Dietrich Klakow

Comments Accepted at Practical Machine Learning For Developing Countries @ ICLR 2021

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

Benjamin Eysenbach, Swapnil Asawa, Shreyas Chaudhari, Sergey Levine, Ruslan Salakhutdinov

Comments Published at ICLR 2021. Code (https://github.com/google-research/google-research/tree/master/darc) and blog post (https://blog.ml.cmu.edu/2020/07/31/maintaining-the-illusion-of-reality-transfer-in-rl-by-keeping-agents-in-the-darc)

Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches

Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre, Mateja Jamnik, Pietro Liò, Adrian Weller

Comments Presented at the RAI, WeaSul, and RobustML workshops at The Ninth International Conference on Learning Representations (ICLR) 2021

Can Active Learning Preemptively Mitigate Fairness Issues?

Frédéric Branchaud-Charron, Parmida Atighehchian, Pau Rodríguez, Grace Abuhamad, Alexandre Lacoste

Comments Presented at ICLR 2021 Workshop on Responsable AI

Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction

Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong

Comments Accepted as a conference paper at ICLR 2021

Towards Causal Federated Learning For Enhanced Robustness and Privacy

Sreya Francis, Irene Tenison, Irina Rish

Journal ref ICLR 2021 Distributed and Private Machine Learning(DPML) Workshop

Inference of cell dynamics on perturbation data using adjoint sensitivity

Weiqi Ji, Bo Yuan, Ciyue Shen, Aviv Regev, Chris Sander, Sili Deng

Comments Accepted as a workshop paper at ICLR 2021 SimDL Workshop

PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN

Daniele Romanini, Adam James Hall, Pavlos Papadopoulos, Tom Titcombe, Abbas Ismail, Tudor Cebere, Robert Sandmann, Robin Roehm, Michael A. Hoeh

Comments ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots

Comments 15 pages

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

Selective Classification Can Magnify Disparities Across Groups

Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang

Comments Published at the International Conference on Learning Representations (ICLR) 2021

A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks

Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora

Comments This version is the camera-ready version for ICLR 2021. Main changes include a detailed discussion about natural tasks, more detailed proof sketch and updated experimental evaluations

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Vitaly Kurin, Maximilian Igl, Tim Rocktäschel, Wendelin Boehmer, Shimon Whiteson

Comments ICLR 2021 Camera-Ready Version

MultiModalQA: Complex Question Answering over Text, Tables and Images

Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, Jonathan Berant

Comments ICLR 2021

Finite Volume Neural Network: Modeling Subsurface Contaminant Transport

Timothy Praditia, Matthias Karlbauer, Sebastian Otte, Sergey Oladyshkin, Martin V. Butz, Wolfgang Nowak

Comments Published as a workshop paper at ICLR 2021 SimDL Workshop