ICLR

NTK-SAP: Improving neural network pruning by aligning training dynamics

Yite Wang, Dawei Li, Ruoyu Sun

Comments Accepted at ICLR 2023 (https://openreview.net/forum?id=-5EWhW_4qWP). Our code will be released at https://github.com/YiteWang/NTK-SAP

Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation

Hanrong Ye, Dan Xu

Comments A supplementary document for "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" accepted by ICLR 2023. Project page: https://github.com/prismformore/Multi-Task-Transformer/tree/main/TaskPrompter

Journal ref ICLR 2023

Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework

Corinna Coupette, Sebastian Dalleiger, Bastian Rieck

Comments Accepted at ICLR 2023 (https://openreview.net/forum?id=sPCKNl5qDps)

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

Jinrong Yang, Lin Song, Songtao Liu, Weixin Mao, Zeming Li, Xiaoping Li, Hongbin Sun, Jian Sun, Nanning Zheng

Comments ICLR 2023. Code at https://github.com/yancie-yjr/DBQ-SSD

EigenFold: Generative Protein Structure Prediction with Diffusion Models

Bowen Jing, Ezra Erives, Peter Pao-Huang, Gabriele Corso, Bonnie Berger, Tommi Jaakkola

Comments ICLR MLDD workshop 2023

Boosting Adversarial Transferability using Dynamic Cues

Muzammal Naseer, Ahmad Mahmood, Salman Khan, Fahad Khan

Comments International Conference on Learning Representations (ICLR'23), Code:https://bit.ly/3Xd9gRQ

Jointly Learning Visual and Auditory Speech Representations from Raw Data

Alexandros Haliassos, Pingchuan Ma, Rodrigo Mira, Stavros Petridis, Maja Pantic

Comments ICLR 2023. Code: https://github.com/ahaliassos/raven

A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification

Paul F. Jaeger, Carsten T. Lüth, Lukas Klein, Till J. Bungert

Journal ref ICLR 2023 (oral)

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

Jung-Woo Chang, Nojan Sheybani, Shehzeen Samarah Hussain, Mojan Javaheripi, Seira Hidano, Farinaz Koushanfar

Comments 8 pages; Accepted to ICLR 2023 ML4IoT workshop

Geometric constraints improve inference of sparsely observed stochastic dynamics

Dimitra Maoutsa

Comments 8+9 pages; 4 figures ; Accepted to ICLR 2023 workshop on Physics for Machine Learning. An earlier account of this work has been previously appeared in arXiv:2301.08102

Almost Linear Constant-Factor Sketching for $\ell_1$ and Logistic Regression

Alexander Munteanu, Simon Omlor, David Woodruff

Comments ICLR 2023

AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

Chris Chinenye Emezue, Sanchit Gandhi, Lewis Tunstall, Abubakar Abid, Josh Meyer, Quentin Lhoest, Pete Allen, Patrick Von Platen, Douwe Kiela, Yacine Jernite, Julien Chaumond, Merve Noyan, Omar Sanseviero

Comments Accepted to the AfricaNLP Workshop at ICLR 2023

Amortised Invariance Learning for Contrastive Self-Supervision

Ruchika Chavhan, Henry Gouk, Jan Stuehmer, Calum Heggan, Mehrdad Yaghoobi, Timothy Hospedales

Comments ICLR 2023, Code available here: https://github.com/ruchikachavhan/amortized-invariance-learning-ssl/

Memorization-Dilation: Modeling Neural Collapse Under Label Noise

Duc Anh Nguyen, Ron Levie, Julian Lienen, Gitta Kutyniok, Eyke Hüllermeier

Comments to be published at ICLR 2023

Depth Separation with Multilayer Mean-Field Networks

Yunwei Ren, Mo Zhou, Rong Ge

Comments ICLR 2023

BOLLWM: A real-world dataset for bollworm pest monitoring from cotton fields in India

Jerome White, Chandan Agrawal, Anmol Ojha, Apoorv Agnihotri, Makkunda Sharma, Jigar Doshi

Journal ref ICLR 2023 workshop on Practical Machine Learning for Developing Countries

Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models

Kaiyue Wen, Jiaye Teng, Jingzhao Zhang

Comments Published as a conference paper at ICLR 2023

Mini-batch $k$-means terminates within $O(d/ε)$ iterations

Gregory Schwartzman

Comments ICLR 2023

Scientific Computing Algorithms to Learn Enhanced Scalable Surrogates for Mesh Physics

Brian R. Bartoldson, Yeping Hu, Amar Saini, Jose Cadena, Yucheng Fu, Jie Bao, Zhijie Xu, Brenda Ng, Phan Nguyen

Comments ICLR 2023 Workshop on Physics for Machine Learning

Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability

Haoyi Xiong, Xuhong Li, Boyang Yu, Zhanxing Zhu, Dongrui Wu, Dejing Dou

Comments The complete manuscript of our previous submission to ICLR'21 (https://openreview.net/forum?id=g4szfsQUdy3). This manuscript was major done in 2021. We gave try to some venues but unfortunately haven't made it accepted yet

Predictive Heterogeneity: Measures and Applications

Jiashuo Liu, Jiayun Wu, Bo Li, Peng Cui

Comments 35 pages. Short version accepted at ICLR 2023

Improving extreme weather events detection with light-weight neural networks

Romain Lacombe, Hannah Grossman, Lucas Hendren, David Lüdeke

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

E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics

Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Stefan Adami, Nikolaus A. Adams

Comments ICLR 2023 Workshop on Physics for Machine Learning

Vision-based route following by an embodied insect-inspired sparse neural network

Lu Yihe, Rana Alkhoury Maroun, Barbara Webb

Comments 8 pages, 4 figures; work-in-progress submission, accepted as a poster at ICLR 2023 Workshop on Sparsity in Neural Networks; non-archival

Physics-driven machine learning models coupling PyTorch and Firedrake

Nacime Bouziani, David A. Ham

Comments Accepted at the ICLR 2023 Workshop on Physics for Machine Learning

Chasing Low-Carbon Electricity for Practical and Sustainable DNN Training

Zhenning Yang, Luoxi Meng, Jae-Won Chung, Mosharaf Chowdhury

Comments ICLR 23 Workshop | https://ml.energy/zeus

Evaluation Challenges for Geospatial ML

Esther Rolf

Comments ICLR 2023 Workshop on Machine Learning for Remote Sensing

Editing Models with Task Arithmetic

Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, Ali Farhadi

Comments In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023)

How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization

Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson

Comments 31 pages, 29 figures. To be presented at ICLR 2023. Code at https://github.com/JonasGeiping/dataaugs

Continual evaluation for lifelong learning: Identifying the stability gap

Matthias De Lange, Gido van de Ven, Tinne Tuytelaars

Comments Published as spotlight paper at ICLR 2023