NeurIPS

Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions

Antonio Terpin, Nicolas Lanzetti, Batuhan Yardim, Florian Dörfler, Giorgia Ramponi

Comments Accepted for presentation at, and publication in the proceedings of, the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Large-batch Optimization for Dense Visual Predictions

Zeyue Xue, Jianming Liang, Guanglu Song, Zhuofan Zong, Liang Chen, Yu Liu, Ping Luo

Comments 23 pages, 6 figures

Journal ref NeurIPS 2022

Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection

Abir De, Soumen Chakrabarti

Journal ref NeurIPS 2022

Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models

Haoyue Dai, Peter Spirtes, Kun Zhang

Comments accepted to NeurIPS 2022

Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks

Indradyumna Roy, Soumen Chakrabarti, Abir De

Journal ref NeurIPS 2022

Towards Sustainable Self-supervised Learning

Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Comments Extension of NeurIPS 2022 workshop

Grounded Video Situation Recognition

Zeeshan Khan, C. V. Jawahar, Makarand Tapaswi

Comments Accepted to NeurIPS 2022. Project Page: https://zeeshank95.github.io/grvidsitu

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

Jiaxin Zhang, Yashar Moshfeghi

Comments Accepted to NeurIPS 2022

MOVE: Unsupervised Movable Object Segmentation and Detection

Adam Bielski, Paolo Favaro

Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Poisson Flow Generative Models

Yilun Xu, Ziming Liu, Max Tegmark, Tommi Jaakkola

Comments Accepted by NeurIPS 2022

OmniVL:One Foundation Model for Image-Language and Video-Language Tasks

Junke Wang, Dongdong Chen, Zuxuan Wu, Chong Luo, Luowei Zhou, Yucheng Zhao, Yujia Xie, Ce Liu, Yu-Gang Jiang, Lu Yuan

Comments To appear at NeurIPs 2022, Camera Ready with Typos fixed

SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks

Davide Buffelli, Pietro Liò, Fabio Vandin

Comments Accepted at NeurIPS 2022

Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers

Ran Liu, Mehdi Azabou, Max Dabagia, Jingyun Xiao, Eva L. Dyer

Comments accepted by NeurIPS 2022

On Margins and Generalisation for Voting Classifiers

Felix Biggs, Valentina Zantedeschi, Benjamin Guedj

Comments 20 pages, 8 figures

Journal ref 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Rashomon Capacity: A Metric for Predictive Multiplicity in Classification

Hsiang Hsu, Flavio du Pin Calmon

Comments NeurIPS 2022 camera-ready version (34 pages, 23 figures, 2 tables)

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures

Emmanuel Abbe, Samy Bengio, Elisabetta Cornacchia, Jon Kleinberg, Aryo Lotfi, Maithra Raghu, Chiyuan Zhang

Comments To appear in NeurIPS 2022

TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets

Chengrun Yang, Gabriel Bender, Hanxiao Liu, Pieter-Jan Kindermans, Madeleine Udell, Yifeng Lu, Quoc Le, Da Huang

Comments NeurIPS 2022; 30 pages, 15 figures, 7 tables

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, James Zou

Comments Published at NeurIPS 2022. Code and data are available at https://modalitygap.readthedocs.io/

Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning

Byungchan Ko, Jungseul Ok

Journal ref Neurips 2022

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

Pengfei Li, Beiwen Tian, Yongliang Shi, Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang

Comments Accepted by NeurIPS 2022. Codes are available at https://github.com/AIR-DISCOVER/TOIST

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

Annie Xie, Fahim Tajwar, Archit Sharma, Chelsea Finn

Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image Models

Ricardo Kleinlein, Cristina Luna-Jiménez, Fernando Fernández-Martínez

Comments NeurIPS 2022 Machine Learning for Creativity and Design Workshop

Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes

Xinhan Di, Pengqian Yu

Comments Accepted by Reinforcement Learning for Real Life Workshop @ NeurIPS 2022

Convexity Certificates from Hessians

Julien Klaus, Niklas Merk, Konstantin Wiedom, Sören Laue, Joachim Giesen

Comments Accepted for publication at NeurIPS 2022

On the Adversarial Robustness of Mixture of Experts

Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli

Comments Accepted to NeurIPS 2022

Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

Samuel Daulton, Xingchen Wan, David Eriksson, Maximilian Balandat, Michael A. Osborne, Eytan Bakshy

Comments To appear in Advances in Neural Information Processing Systems 35, 2022. Code available at: https://github.com/facebookresearch/bo_pr

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao

Journal ref 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Proximal Learning With Opponent-Learning Awareness

Stephen Zhao, Chris Lu, Roger Baker Grosse, Jakob Nicolaus Foerster

Comments 24 pages (10 pages main paper), 5 figures, to be published in 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Deep Bidirectional Language-Knowledge Graph Pretraining

Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D Manning, Percy Liang, Jure Leskovec

Comments Published at NeurIPS 2022. Code, data, and trained models are available at https://github.com/michiyasunaga/dragon

Neural Attentive Circuits

Nasim Rahaman, Martin Weiss, Francesco Locatello, Chris Pal, Yoshua Bengio, Bernhard Schölkopf, Li Erran Li, Nicolas Ballas

Comments To appear at NeurIPS 2022