ICLR

Large Language Models can Implement Policy Iteration

Ethan Brooks, Logan Walls, Richard L. Lewis, Satinder Singh

Comments 10 pages, 4 figures, submitted to ICLR 2023

Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

Tong Wu, Jiaqi Wang, Xingang Pan, Xudong Xu, Christian Theobalt, Ziwei Liu, Dahua Lin

Comments ICLR 2023 Spotlight. Our code is available at https://github.com/wutong16/Voxurf

ExBEHRT: Extended Transformer for Electronic Health Records to Predict Disease Subtypes & Progressions

Maurice Rupp, Oriane Peter, Thirupathi Pattipaka

Comments ICLR 2023 Workshop on Trustworthy Machine Learning for Healthcare (Website: accepted-papers" target="_blank" rel="noopener">https://sites.google.com/view/tml4h2023/accepted-papers )

Journal ref Lecture Notes in Computer Science, vol 13932. Springer, Cham 2023

Spanish Pre-trained BERT Model and Evaluation Data

José Cañete, Gabriel Chaperon, Rodrigo Fuentes, Jou-Hui Ho, Hojin Kang, Jorge Pérez

Comments Published as workshop paper at Practical ML for Developing Countries Workshop @ ICLR 2020

Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit

Greg Yang, Etai Littwin

Comments This is the complete version of "Adaptive Optimization in the Infinite-Width Limit" in ICLR 2023, https://openreview.net/forum?id=zgVDqw9ZUES

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

Qihao Zhao, Yangyu Huang, Wei Hu, Fan Zhang, Jun Liu

Comments ICLR 2023, 16 pages, 6 figures

Transfer Learning with Deep Tabular Models

Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum

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

Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles

Biswadeep Chakraborty, Saibal Mukhopadhyay

Comments Paper Published in ICLR 2023 (https://openreview.net/forum?id=QIRtAqoXwj)

Journal ref The Eleventh International Conference on Learning Representations 2023

How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?

Jetze T. Schuurmans, Kim Batselier, Julian F. P. Kooij

Comments Published as a conference paper at ICLR 2023. Appendix A.5 was added after the conference

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

Chenxiao Yang, Qitian Wu, Jiahua Wang, Junchi Yan

Comments Accepted to ICLR 2023. Codes in https://github.com/chr26195/PMLP

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, Dacheng Tao, Bernard Ghanem

Comments An extension of our ICLR 2023 paper https://openreview.net/pdf?id=y5W8tpojhtJ. arXiv admin note: text overlap with arXiv:2302.03004

Hebbian Deep Learning Without Feedback

Adrien Journé, Hector Garcia Rodriguez, Qinghai Guo, Timoleon Moraitis

Comments Updated to match the published version of the the ICLR 2023 paper (notable-top 25%)

Journal ref The Eleventh International Conference on Learning Representations (2023) Retrieved from https://openreview.net/forum?id=8gd4M-_Rj1

Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks

Alan Jeffares, Qinghai Guo, Pontus Stenetorp, Timoleon Moraitis

Comments Spotlight paper at ICLR 2022

Journal ref International Conference on Learning Representations. https://openreview.net/forum?id=iMH1e5k7n3L (2022)

CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code

Nadezhda Chirkova, Sergey Troshin

Comments Published at ICLR 2023

On the Universality of the Double Descent Peak in Ridgeless Regression

David Holzmüller

Comments Published at ICLR 2021. 9 pages + 34 pages appendix. Changes in v8: Small corrections. Experimental results can be reproduced using the code at https://github.com/dholzmueller/universal_double_descent

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

Nico Gürtler, Sebastian Blaes, Pavel Kolev, Felix Widmaier, Manuel Wüthrich, Stefan Bauer, Bernhard Schölkopf, Georg Martius

Comments The Eleventh International Conference on Learning Representations. 2022. Published at ICLR 2023. Datasets available at https://github.com/rr-learning/trifinger_rl_datasets

How Do ConvNets Understand Image Intensity?

Jackson Kaunismaa, Michael Guerzhoy

Journal ref ICLR Tiny Papers 2023

FunkNN: Neural Interpolation for Functional Generation

AmirEhsan Khorashadizadeh, Anadi Chaman, Valentin Debarnot, Ivan Dokmanić

Comments 17 pages, 13 figures

Journal ref The 11th International Conference on Learning Representations (ICLR 2023)

Broken Neural Scaling Laws

Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger

Comments Published as a conference paper at International Conference on Learning Representations (ICLR) 2023

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

Minimax Optimal Kernel Operator Learning via Multilevel Training

Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying

Comments ICLR 2023 spotlight

Label Calibration for Semantic Segmentation Under Domain Shift

Ondrej Bohdal, Da Li, Timothy Hospedales

Comments ICLR 2023 Workshop on Pitfalls of Limited Data and Computation for Trustworthy ML

Confidence Estimation Using Unlabeled Data

Chen Li, Xiaoling Hu, Chao Chen

Comments Accepted by ICLR'23

Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples

Qizhang Li, Yiwen Guo, Wangmeng Zuo, Hao Chen

Comments Accepted by ICLR 2023, fix typos

Large Language Models Perform Diagnostic Reasoning

Cheng-Kuang Wu, Wei-Lin Chen, Hsin-Hsi Chen

Comments Accepted as a Tiny Paper at ICLR 2023 (10 pages, 5 figures)

Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation

Zhengrui Ma, Chenze Shao, Shangtong Gui, Min Zhang, Yang Feng

Comments ICLR 2023

Expressive Monotonic Neural Networks

Ouail Kitouni, Niklas Nolte, Michael Williams

Comments 9 pages, 4 figures, ICLR 2023 final submission

Copy Is All You Need

Tian Lan, Deng Cai, Yan Wang, Heyan Huang, Xian-Ling Mao

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

Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer

Zhun Yang, Adam Ishay, Joohyung Lee

Comments 22 pages. The Eleventh International Conference on Learning Representations (ICLR 2023)

Modeling Content Creator Incentives on Algorithm-Curated Platforms

Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, Sarah Dean

Comments presented at ICLR 2023 (top 5%)

FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy

Yan Sun, Li Shen, Tiansheng Huang, Liang Ding, Dacheng Tao

Comments ICLR 2023