NeurIPS

SKFlow: Learning Optical Flow with Super Kernels

Shangkun Sun, Yuanqi Chen, Yu Zhu, Guodong Guo, Ge Li

Comments Accepted to NeurIPS 2022

ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond

Qiming Zhang, Yufei Xu, Jing Zhang, Dacheng Tao

Comments An extended version of the Neurips paper "ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias". arXiv admin note: substantial text overlap with arXiv:2106.03348

Neural Circuit Architectural Priors for Embodied Control

Nikhil X. Bhattasali, Anthony M. Zador, Tatiana A. Engel

Comments NeurIPS 2022

Asymptotics of representation learning in finite Bayesian neural networks

Jacob A. Zavatone-Veth, Abdulkadir Canatar, Benjamin S. Ruben, Cengiz Pehlevan

Comments 13+28 pages, 4 figures; v3: extensive revision with improved exposition and new section on CNNs, accepted to NeurIPS 2021; v4: minor updates to supplement; v5: post-NeurIPS update, minor typos fixed

Journal ref Advances in Neural Information Processing Systems 34 (2021); JSTAT 114008 (2022)

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime

Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová

Comments 22 pages, 10 figures, 2 tables

Journal ref 35th Conference on Neural Information Processing Systems (NeurIPS 2021) vol 34 p10131--10143. J. Stat. Mech. (2022) 114004

Learning curves of generic features maps for realistic datasets with a teacher-student model

Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová

Comments v3: NeurIPS camera-ready

Journal ref 35th Conference on Neural Information Processing Systems (NeurIPS 2021), vol 34 p10137--18151. J. Stat. Mech. (2022) 114001

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages

Aristides Milios, Parishad BehnamGhader

Comments Accepted to 2022 Trustworthy and Socially Responsible Machine Learning (TSRML 2022) Workshop at NeurIPS 2022

Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding

Eslam Mohamed Bakr, Yasmeen Alsaedy, Mohamed Elhoseiny

Journal ref NeurIPS 2022

Latent Space Diffusion Models of Cryo-EM Structures

Karsten Kreis, Tim Dockhorn, Zihao Li, Ellen Zhong

Comments Machine Learning for Structural Biology Workshop, NeurIPS 2022 (Oral)

Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning

Zaiyu Huang, Hanhui Li, Zhenyu Xie, Michael Kampffmeyer, Qingling Cai, Xiaodan Liang

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

Assistive Teaching of Motor Control Tasks to Humans

Megha Srivastava, Erdem Biyik, Suvir Mirchandani, Noah Goodman, Dorsa Sadigh

Comments 22 pages, 14 figures, NeurIPS 2022

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Rishi Bommasani, Kathleen A. Creel, Ananya Kumar, Dan Jurafsky, Percy Liang

Comments Published at NeurIPS 2022, presented at EAAMO 2022

Zero-Sum Stochastic Stackelberg Games

Denizalp Goktas, Jiayi Zhao, Amy Greenwald

Comments 29 pages 2 figures, Appeared in NeurIPS'22

End-to-End Stochastic Optimization with Energy-Based Model

Lingkai Kong, Jiaming Cui, Yuchen Zhuang, Rui Feng, B. Aditya Prakash, Chao Zhang

Comments NeurIPS 2022 Oral

Using Selective Masking as a Bridge between Pre-training and Fine-tuning

Tanish Lad, Himanshu Maheshwari, Shreyas Kottukkal, Radhika Mamidi

Comments ENLSP Workshop, NeurIPS 2022

Towards Practical Control of Singular Values of Convolutional Layers

Alexandra Senderovich, Ekaterina Bulatova, Anton Obukhov, Maxim Rakhuba

Comments Published as a conference paper at NeurIPS 2022

Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunIT

Cuneyt Gurcan Akcora, Murat Kantarcioglu, Yulia R. Gel, Baris Coskunuzer

Comments Spotlight paper at NeurIPS 2022

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization

Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson

Comments NeurIPS 2022. Code is available at https://github.com/activatedgeek/tight-pac-bayes

Beyond Mahalanobis-Based Scores for Textual OOD Detection

Pierre Colombo, Eduardo D. C. Gomes, Guillaume Staerman, Nathan Noiry, Pablo Piantanida

Journal ref NeurIPS 2022

Spatial Mixture-of-Experts

Nikoli Dryden, Torsten Hoefler

Comments 20 pages, 3 figures; NeurIPS 2022

Delving into Out-of-Distribution Detection with Vision-Language Representations

Yifei Ming, Ziyang Cai, Jiuxiang Gu, Yiyou Sun, Wei Li, Yixuan Li

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

Graph Contrastive Learning for Materials

Teddy Koker, Keegan Quigley, Will Spaeth, Nathan C. Frey, Lin Li

Comments 7 pages, 3 figures, NeurIPS 2022 AI for Accelerated Materials Design Workshop

Improving the predictions of ML-corrected climate models with novelty detection

Clayton Sanford, Anna Kwa, Oliver Watt-Meyer, Spencer Clark, Noah Brenowitz, Jeremy McGibbon, Christopher Bretherton

Comments Appearing at Tackling Climate Change with Machine Learning Workshop at NeurIPS 2022

Improving dermatology classifiers across populations using images generated by large diffusion models

Luke W. Sagers, James A. Diao, Matthew Groh, Pranav Rajpurkar, Adewole S. Adamson, Arjun K. Manrai

Comments NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research

Rank-One Editing of Encoder-Decoder Models

Vikas Raunak, Arul Menezes

Comments The Second Workshop On Interactive Learning For Natural Language Processing (InterNLP 2022), NeurIPS 2022

Lempel-Ziv Networks

Rebecca Saul, Mohammad Mahmudul Alam, John Hurwitz, Edward Raff, Tim Oates, James Holt

Comments I Can't Believe It's Not Better Workshop at NeurIPS 2022

Relating Regularization and Generalization through the Intrinsic Dimension of Activations

Bradley C. A. Brown, Jordan Juravsky, Anthony L. Caterini, Gabriel Loaiza-Ganem

Comments NeurIPS 2022 OPT and HITY workshops

Equality of Effort via Algorithmic Recourse

Francesca E. D. Raimondi, Andrew R. Lawrence, Hana Chockler

Journal ref Presented at the Algorithmic Fairness through the Lens of Causality and Privacy Workshop at Neural Information Processing Systems, 2022

Data-Driven Offline Decision-Making via Invariant Representation Learning

Han Qi, Yi Su, Aviral Kumar, Sergey Levine

Comments This is an extended version of the NeurIPS 2022 conference paper titled: "Data-Driven Offline Model-Based Optimization via Invariant Representation Learning"

Validation Diagnostics for SBI algorithms based on Normalizing Flows

Julia Linhart, Alexandre Gramfort, Pedro L. C. Rodrigues

Comments 7 pages, 2 figures, 1 appendix, published at "Machine Learning and the Physical Sciences" workshop (NeurIPS 2022): https://ml4physicalsciences.github.io/2022/