ICLR

Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning

Sasha Salter, Kristian Hartikainen, Walter Goodwin, Ingmar Posner

Journal ref Published at the International Conference on Learning Representations, 2023

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

Kuo-Hao Zeng, Luca Weihs, Roozbeh Mottaghi, Ali Farhadi

Comments 21 pages, 17 figures, ICLR 2023

Function-Consistent Feature Distillation

Dongyang Liu, Meina Kan, Shiguang Shan, Xilin Chen

Comments ICLR 2023

Adaptive-saturated RNN: Remember more with less instability

Khoi Minh Nguyen-Duy, Quang Pham, Binh T. Nguyen

Comments 8 pages, 2 figures, 5 tables, ICLR 2023 Tiny Paper Track

Journal ref ICLR 2023 Tiny Paper Track

DiffESM: Conditional Emulation of Earth System Models with Diffusion Models

Seth Bassetti, Brian Hutchinson, Claudia Tebaldi, Ben Kravitz

Comments Presented at Tackling Climate Change with Machine Learning, ICLR 2023

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Weixuan Wang, Siqin Li, Xianliang Wang, Xianhan Zeng, Rundong Wang, Jiawei Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

Comments Accepted at ICLR 2023

Learning Symbolic Representations Through Joint GEnerative and DIscriminative Training

Emanuele Sansone, Robin Manhaeve

Comments ICLR 2023 Workshop NeSy-GeMs. arXiv admin note: substantial text overlap with arXiv:2212.13425

Journal ref ICLR 2023 Workshop NeSy-GeMs

DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation

Qiaoyue Tang, Mathias Lécuyer

Comments Published at ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models

Guarded Policy Optimization with Imperfect Online Demonstrations

Zhenghai Xue, Zhenghao Peng, Quanyi Li, Zhihan Liu, Bolei Zhou

Comments Accepted at ICLR 2023 (top 25%)

Learning Multimodal Data Augmentation in Feature Space

Zichang Liu, Zhiqiang Tang, Xingjian Shi, Aston Zhang, Mu Li, Anshumali Shrivastava, Andrew Gordon Wilson

Comments ICLR 2023. Code available at https://github.com/lzcemma/LeMDA/

Retrieval-based Controllable Molecule Generation

Zichao Wang, Weili Nie, Zhuoran Qiao, Chaowei Xiao, Richard Baraniuk, Anima Anandkumar

Comments ICLR 2023

Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

Nihal V. Nayak, Peilin Yu, Stephen H. Bach

Comments ICLR 2023

Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis

Vithya Yogarajan, Gillian Dobbie, Henry Gouk

Comments accepted with invite to present

Journal ref ICLR TinyPaper 2023

Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions

Lina Mezghani, Piotr Bojanowski, Karteek Alahari, Sainbayar Sukhbaatar

Journal ref Reincarnating Reinforcement Learning Workshop at ICLR 2023

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

Florent Delgrange, Ann Nowé, Guillermo A. Pérez

Comments ICLR 2023, 10 pages main text, 14 pages appendix (excluding references)

Graph-Relational Domain Adaptation

Zihao Xu, Hao He, Guang-He Lee, Yuyang Wang, Hao Wang

Comments Accepted by ICLR 2022

Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization

Stamatios Lefkimmiatis, Iaroslav Koshelev

Comments Paper has been accepted and will appear at ICLR 2023 proceedings. Link to OpenReview: https://openreview.net/forum?id=TXPN6MtdSE4

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine

Comments 26 pages, 18 figures, 3 tables, The International Conference on Learning Representations (ICLR) 2023

Revisiting Implicit Neural Representations in Low-Level Vision

Wentian Xu, Jianbo Jiao

Comments Published at the ICLR 2023 Neural Fields workshop. Project Webpage: https://wentxul.github.io/LINR-projectpage

LipsFormer: Introducing Lipschitz Continuity to Vision Transformers

Xianbiao Qi, Jianan Wang, Yihao Chen, Yukai Shi, Lei Zhang

Comments To appear in ICLR 2023, our code will be public at https://github.com/IDEA-Research/LipsFormer

Generalization and Estimation Error Bounds for Model-based Neural Networks

Avner Shultzman, Eyar Azar, Miguel R. D. Rodrigues, Yonina C. Eldar

Journal ref The Eleventh International Conference on Learning Representations, 2023

The Responsibility Problem in Neural Networks with Unordered Targets

Ben Hayes, Charalampos Saitis, György Fazekas

Comments Accepted for TinyPaper archival at ICLR 2023: https://openreview.net/forum?id=jd7Hy1jRiv4

Martingale Posterior Neural Processes

Hyungi Lee, Eunggu Yun, Giung Nam, Edwin Fong, Juho Lee

Comments ICLR 2023

Decoupled Training for Long-Tailed Classification With Stochastic Representations

Giung Nam, Sunguk Jang, Juho Lee

Comments ICLR 2023

Constraining Representations Yields Models That Know What They Don't Know

Joao Monteiro, Pau Rodriguez, Pierre-Andre Noel, Issam Laradji, David Vazquez

Comments CR version published at ICLR 2023

Imbalanced Domain Generalization for Robust Single Cell Classification in Hematological Cytomorphology

Rao Muhammad Umer, Armin Gruber, Sayedali Shetab Boushehri, Christian Metak, Carsten Marr

Comments Published at ICLR 2023 Workshop on Domain Generalization

Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes

Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine

Comments Accepted at ICLR 2023. Project website: https://sites.google.com/view/scaling-offlinerl/home

Particle-based Variational Inference with Preconditioned Functional Gradient Flow

Hanze Dong, Xi Wang, Yong Lin, Tong Zhang

Comments 26 pages, 8 figures, ICLR 2023

XAI for transparent wind turbine power curve models

Simon Letzgus

Comments Accepted as a workshop paper at 'Tackling Climate Change with Machine Learning', ICLR 2023

Learning differentiable solvers for systems with hard constraints

Geoffrey Négiar, Michael W. Mahoney, Aditi S. Krishnapriyan

Comments Paper accepted to the 11th International Conference on Learning Representations (ICLR 2023). 9 pages + references + appendix. 5 figures in main text