NeurIPS

Learning Equilibria in Matching Markets from Bandit Feedback

Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt

Comments Accepted to the Journal of the ACM; conference version appeared at NeurIPS 2021

Are Defenses for Graph Neural Networks Robust?

Felix Mujkanovic, Simon Geisler, Stephan Günnemann, Aleksandar Bojchevski

Comments 34 pages, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Deep Learning for Reference-Free Geolocation for Poplar Trees

Cai W. John, Owen Queen, Wellington Muchero, Scott J. Emrich

Comments Accepted at NeurIPS 2022 AI for Science Workshop

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?

Nikolaos Tsilivis, Julia Kempe

Comments NeurIPS 2022; added link to GitHub repository

The Efficacy of Self-Supervised Speech Models for Audio Representations

Tung-Yu Wu, Chen-An Li, Tzu-Han Lin, Tsu-Yuan Hsu, Hung-Yi Lee

Comments to appear in Proceedings of Machine Learning Research (PMLR): NeurIPS 2021 Competition Track

Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics

Max Schrader, Navish Kumar, Nicolas Collignon, Esben Sørig, Soonmyeong Yoon, Akash Srivastava, Kai Xu, Maria Astefanoaei

Journal ref NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning

Doubly Robust Counterfactual Classification

Kwangho Kim, Edward H. Kennedy, José R. Zubizarreta

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

Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov

Comments Accepted at 3rd Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2022. Source code: https://github.com/tinkoff-ai/cnf

Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size

Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Dmitry Akimov, Sergey Kolesnikov

Comments Accepted at 3rd Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2022. Source code: https://github.com/tinkoff-ai/lb-sac

Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations

Ramansh Sharma, Varun Shankar

Comments Accepted at the 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022)

Chaos as an interpretable benchmark for forecasting and data-driven modelling

William Gilpin

Comments 10 pages, 4 figures, plus appendices

Journal ref NeurIPS (Neural Information Processing Systems) 2021

RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks

Leo Kozachkov, Michaela Ennis, Jean-Jacques Slotine

Comments Published as a conference paper at NeurIPS 2022

Optimal Policies Tend to Seek Power

Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli

Comments Accepted to NeurIPS 2021 as spotlight paper. 12 pages, 44 pages with appendices. Since the 2021 acceptance, we updated the paper to point out that optimal policies can be qualitatively divorced from real-world learned policies

CROWDLAB: Supervised learning to infer consensus labels and quality scores for data with multiple annotators

Hui Wen Goh, Ulyana Tkachenko, Jonas Mueller

Journal ref NeurIPS 2022 Human in the Loop Learning Workshop

Myriad: a real-world testbed to bridge trajectory optimization and deep learning

Nikolaus H. R. Howe, Simon Dufort-Labbé, Nitarshan Rajkumar, Pierre-Luc Bacon

Comments Updated to match version accepted at NeurIPS 2022

Neural Abstractions

Alessandro Abate, Alec Edwards, Mirco Giacobbe

Comments NeurIPS 2022

A Closer Look at Novel Class Discovery from the Labeled Set

Ziyun Li, Jona Otholt, Ben Dai, Di hu, Christoph Meinel, Haojin Yang

Comments Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields

Ilyes Batatia, Dávid Péter Kovács, Gregor N. C. Simm, Christoph Ortner, Gábor Csányi

Comments Advances in Neural Information Processing Systems, 2022

Challenging Common Assumptions in Convex Reinforcement Learning

Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli

Comments NeurIPS 2022

Certified Interpretability Robustness for Class Activation Mapping

Alex Gu, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Comments 13 pages, 5 figures. Accepted to Machine Learning for Autonomous Driving Workshop at NeurIPS 2020

Efficient Aggregated Kernel Tests using Incomplete $U$-statistics

Antonin Schrab, Ilmun Kim, Benjamin Guedj, Arthur Gretton

Comments 34 pages, 5 figures

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

Flowification: Everything is a Normalizing Flow

Bálint Máté, Samuel Klein, Tobias Golling, François Fleuret

Comments NeurIPS 2022

Iterative Teaching by Label Synthesis

Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller

Comments NeurIPS 2021 Spotlight (v5: 28 pages, 20 figures, fixed typos in v4)

Off-Policy Evaluation for Action-Dependent Non-Stationary Environments

Yash Chandak, Shiv Shankar, Nathaniel D. Bastian, Bruno Castro da Silva, Emma Brunskil, Philip S. Thomas

Comments Accepted at Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

Interaction Modeling with Multiplex Attention

Fan-Yun Sun, Isaac Kauvar, Ruohan Zhang, Jiachen Li, Mykel Kochenderfer, Jiajun Wu, Nick Haber

Comments NeurIPS 2022, project website: https://cs.stanford.edu/~sunfanyun/imma/

VN-Transformer: Rotation-Equivariant Attention for Vector Neurons

Serge Assaad, Carlton Downey, Rami Al-Rfou, Nigamaa Nayakanti, Ben Sapp

Comments Published in Transactions on Machine Learning Research (TMLR), 2023; Previous version appeared in Workshop on Machine Learning for Autonomous Driving, Conference on Neural Information Processing Systems (NeurIPS), 2022

A Boosting Approach to Reinforcement Learning

Nataly Brukhim, Elad Hazan, Karan Singh

Comments Now in sync with camera ready for NeurIPS 2022

Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs

Tao Liu, Ruida Zhou, Dileep Kalathil, P. R. Kumar, Chao Tian

Comments Appear in NeurIPS 2021. Revise Algorithm 2 and proof of Lemma 5.6

Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel

Changyong Oh, Roberto Bondesan, Efstratios Gavves, Max Welling

Comments NeurIPS 2022

Towards dynamic stability analysis of sustainable power grids using graph neural networks

Christian Nauck, Michael Lindner, Konstantin Schürholt, Frank Hellmann

Comments main section: 4 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2206.06369

Journal ref NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning