ICML

Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems

Manuel Brenner, Florian Hess, Jonas M. Mikhaeil, Leonard Bereska, Zahra Monfared, Po-Chen Kuo, Daniel Durstewitz

Comments To be published in the Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition

Zheng Wang, Shandian Zhe

Comments 9 pages, ICML 2022

BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection

Asiegbu Miracle Kanu-Asiegbu, Ram Vasudevan, Xiaoxiao Du

Comments Accepted in Workshop on Safe Learning for Autonomous Driving, co-located with the International Conference on Machine Learning (ICML 20222)

Offline RL Policies Should be Trained to be Adaptive

Dibya Ghosh, Anurag Ajay, Pulkit Agrawal, Sergey Levine

Comments ICML 2022 (long talk)

Efficient Representation Learning via Adaptive Context Pooling

Chen Huang, Walter Talbott, Navdeep Jaitly, Josh Susskind

Comments ICML 2022

Discrete Tree Flows via Tree-Structured Permutations

Mai Elkady, Jim Lim, David I. Inouye

Comments Accepted to ICML 2022

Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space

Shivansh Beohar, Fabian Heinrich, Rahul Kala, Helge Ritter, Andrew Melnik

Comments Published in SL4AD Workshop, ICML 2022

Evaluation of Semantic Answer Similarity Metrics

Farida Mustafazade, Peter F. Ebbinghaus

Comments 3rd International Conference on NLP & Big Data (NLPD 2022), 4th International Conference on Machine Learning & Applications (CMLA 2022)

Journal ref IJNLC June 2022, Volume 11, Number 3

Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets

Hongxin Wei, Lue Tao, Renchunzi Xie, Lei Feng, Bo An

Comments Accepted by ICML 2022

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

Changbin Li, Suraj Kothawade, Feng Chen, Rishabh Iyer

Comments *Equal Contribution. In proceedings of the Thirty-ninth International Conference on Machine Learning , ICML 2022

Rethinking Attention-Model Explainability through Faithfulness Violation Test

Yibing Liu, Haoliang Li, Yangyang Guo, Chenqi Kong, Jing Li, Shiqi Wang

Comments Accepted to ICML 2022

Learning Stochastic Shortest Path with Linear Function Approximation

Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu

Comments 46 pages, 1 figure. In ICML 2022

One-Shot Transfer Learning of Physics-Informed Neural Networks

Shaan Desai, Marios Mattheakis, Hayden Joy, Pavlos Protopapas, Stephen Roberts

Comments ICML AI4Science Workshop 2022

LSB: Local Self-Balancing MCMC in Discrete Spaces

Emanuele Sansone

Comments ICML 2022

On the Practicality of Deterministic Epistemic Uncertainty

Janis Postels, Mattia Segu, Tao Sun, Luca Sieber, Luc Van Gool, Fisher Yu, Federico Tombari

Comments International Conference on Machine Learning 2022

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition

Haotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng, Mu Li, Alex Smola, Zhangyang Wang

Comments ICML 2022

Removing Batch Normalization Boosts Adversarial Training

Haotao Wang, Aston Zhang, Shuai Zheng, Xingjian Shi, Mu Li, Zhangyang Wang

Comments ICML 2022

ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias

Yupu Lu, Shijie Lin, Guanqi Chen, Jia Pan

Comments Accepted by ICML 2022

Gradient-Based Adversarial and Out-of-Distribution Detection

Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib

Comments International Conference on Machine Learning (ICML) Workshop on New Frontiers in Adversarial Machine Learning, July 2022

Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers

Rui Liu, Young Jin Kim, Alexandre Muzio, Hany Hassan Awadalla

Comments Accepted to ICML 2022

Pixelated Reconstruction of Gravitational Lenses using Recurrent Inference Machines

Alexandre Adam, Laurence Perreault-Levasseur, Yashar Hezaveh

Comments 4+10 pages, 4+5 figures, accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics

NP-Match: When Neural Processes meet Semi-Supervised Learning

Jianfeng Wang, Thomas Lukasiewicz, Daniela Massiceti, Xiaolin Hu, Vladimir Pavlovic, Alexandros Neophytou

Comments To appear at ICML 2022. The source codes are at https://github.com/Jianf-Wang/NP-Match

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

Edoardo Cetin, Philip J. Ball, Steve Roberts, Oya Celiktutan

Comments Short presentation at ICML 2022

On Convergence of Gradient Descent Ascent: A Tight Local Analysis

Haochuan Li, Farzan Farnia, Subhro Das, Ali Jadbabaie

Comments Accepted by ICML 2022

Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity

Jianyi Yang, Shaolei Ren

Comments Accepted by ICML'22

ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy

Daniel Zeng, Tailin Wu, Jure Leskovec

Comments ICML 2022 Beyond Bayes: Paths Towards Universal Reasoning Systems Workshop; 17 pages, 10 figures

Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language

Iou-Jen Liu, Xingdi Yuan, Marc-Alexandre Côté, Pierre-Yves Oudeyer, Alexander G. Schwing

Comments ICML 2022; Project page: https://ioujenliu.github.io/AFK/

Tractable Uncertainty for Structure Learning

Benjie Wang, Matthew Wicker, Marta Kwiatkowska

Comments ICML 2022 (long talk); 20 pages

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt

Comments ICML 2022. The last three authors contributed equally

SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation

Giorgio Giannone, Ole Winther

Comments ICML 2022