ICLR

LAVA: Data Valuation without Pre-Specified Learning Algorithms

Hoang Anh Just, Feiyang Kang, Jiachen T. Wang, Yi Zeng, Myeongseob Ko, Ming Jin, Ruoxi Jia

Comments ICLR 2023 Spotlight Latest Updated Version: 2023/12/19

Efficient Conditionally Invariant Representation Learning

Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton

Comments ICLR 2023

Journal ref The Eleventh International Conference on Learning Representations, 2023

Hierarchical Autoregressive Modeling for Neural Video Compression

Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

Comments Published as a conference paper at ICLR 2021

FigGen: Text to Scientific Figure Generation

Juan A Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

Comments Published at ICLR 2023 as a Tiny Paper

Acting in Delayed Environments with Non-Stationary Markov Policies

Esther Derman, Gal Dalal, Shie Mannor

Comments Published in ICLR 2021

ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations

Xuyang Zhao, Tianqi Du, Yisen Wang, Jun Yao, Weiran Huang

Comments Accepted by ICLR 2023

SAM as an Optimal Relaxation of Bayes

Thomas Möllenhoff, Mohammad Emtiyaz Khan

Comments Accepted at ICLR 2023. Changes: Link to source code (https://github.com/team-approx-bayes/bayesian-sam), fix a typo in Appendix D

Reinforcement Learning for Combining Search Methods in the Calibration of Economic ABMs

Aldo Glielmo, Marco Favorito, Debmallya Chanda, Domenico Delli Gatti

Comments 9 pages and 5 figures, presented at the AAAI bridge program 'AI for Financial Institutions' (https://aaai23.bankit.art/), at the ICLR bridge program 'AI4ABM' (https://ai4abm.org/workshop_iclr2023/) and at ICAIF '23 (https://ai-finance.org/). Proceedings of the Fourth ACM International Conference on AI in Finance, (ICAIF 23), Association for Computing Machinery, New York, NY, USA

InfoBot: Transfer and Exploration via the Information Bottleneck

Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio, Sergey Levine

Comments Accepted at ICLR'19

Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Rajkumar Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, Yejin Choi

Comments In Proceedings of ICLR 2023. Code found at https://github.com/allenai/rl4lms and Project website at https://rl4lms.apps.allenai.org/

Universalizing Weak Supervision

Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Roberts, Frederic Sala

Comments ICLR 2022

Zero-Shot Self-Supervised Learning for MRI Reconstruction

Burhaneddin Yaman, Seyed Amir Hossein Hosseini, Mehmet Akçakaya

Journal ref International Conference on Learning Representations (ICLR), 2022

Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks

Lennart Brocki, Neo Christopher Chung

Journal ref ICLR 2023 Workshop on Trustworthy ML; Full Paper in Pattern Recognition Letters

Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing

Sai Praneeth Karimireddy, Lie He, Martin Jaggi

Comments v5 is the camera-ready version of this paper on ICLR 2022

Neural Bregman Divergences for Distance Learning

Fred Lu, Edward Raff, Francis Ferraro

Comments Published in ICLR 2023, more related works added

ToolTalk: Evaluating Tool-Usage in a Conversational Setting

Nicholas Farn, Richard Shin

Comments 10 pages, 1 figure, ICLR 2024 Submission, https://github.com/microsoft/ToolTalk

Lesion Search with Self-supervised Learning

Kristin Qi, Jiali Cheng, Daniel Haehn

Comments ICLR 2023 Tiny Paper

Multiparameter Persistent Homology for Molecular Property Prediction

Andac Demir, Bulent Kiziltan

Comments ICLR 2023-Machine Learning for Drug Discovery. arXiv admin note: text overlap with arXiv:2211.03808

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths

Comments Under review at ICLR 2024

A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity

Hongkang Li, Meng Wang, Sijia Liu, Pin-yu Chen

Journal ref ICLR 2023

Guaranteed Conformance of Neurosymbolic Models to Natural Constraints

Kaustubh Sridhar, Souradeep Dutta, James Weimer, Insup Lee

Comments Accepted to L4DC 2023 and Neurosymbolic Generative Models workshop, ICLR 2023

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Hyunwoo Ryu, Hong-in Lee, Jeong-Hoon Lee, Jongeun Choi

Comments 32 pages, 14 figures, To appear in the Eleventh International Conference on Learning Representations (ICLR) 2023

Journal ref The Eleventh International Conference on Learning Representations (ICLR), 2023

Importance Estimation with Random Gradient for Neural Network Pruning

Suman Sapkota, Binod Bhattarai

Comments 7 pages, 2 figures, ICLR 2023 Workshop on Sparsity in Neural Networks. arXiv admin note: text overlap with arXiv:2306.13203

Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning

Alihan Hüyük, Daniel Jarrett, Mihaela van der Schaar

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

Autoregressive Renaissance in Neural PDE Solvers

Yolanne Yi Ran Lee

Comments Presented as a workshop poster at ICLR 2023

Robustifying Language Models with Test-Time Adaptation

Noah Thomas McDermott, Junfeng Yang, Chengzhi Mao

Comments 8 Pages 2 Figures Submitted to ICLR Workshop

On the Sensitivity of Reward Inference to Misspecified Human Models

Joey Hong, Kush Bhatia, Anca Dragan

Comments published as a paper in ICLR 2023; 17 pages, 12 figures

Confidence-Conditioned Value Functions for Offline Reinforcement Learning

Joey Hong, Aviral Kumar, Sergey Levine

Comments published as a paper in ICLR 2023; 16 pages

Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems

D'Jeff Kanda Nkashama, Arian Soltani, Jean-Charles Verdier, Marc Frappier, Pierre-Martin Tardif, Froduald Kabanza

Comments Machine Learning for Cybersecurity Workshop at the International Conference on Machine Learning(ICLR-ML4CY)

Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation

Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui

Comments $\textbf{v1-v4}$ (Early 2022): Initially announced with the name "Generalized Aggressive Decoding"; $\textbf{v5}$ (September 2022): Renamed to "Speculative Decoding" as the ICLR'23 submission (https://openreview.net/pdf?id=H-VlwsYvVi), marking $\textbf{the first time}$ "Speculative Decoding" has been publicly proposed. $\textbf{v6}$: EMNLP'23 Findings camera ready