NeurIPS

Reproducibility in Optimization: Theoretical Framework and Limits

Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir

Comments 45 Pages; Accepted to NeurIPS 2022

Adjoint-aided inference of Gaussian process driven differential equations

Paterne Gahungu, Christopher W Lanyon, Mauricio A Alvarez, Engineer Bainomugisha, Michael Smith, Richard D. Wilkinson

Comments 22 pages, 11 figures, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Neuroevolution deep learning architecture search for estimation of river surface elevation from photogrammetric Digital Surface Models

Radosław Szostak, Marcin Pietroń, Mirosław Zimnoch, Przemysław Wachniew, Paweł Ćwiąkała, Edyta Puniach

Comments extended version of NeurIPS 2021 Workshop paper - ML4PhysicalSciences

Algorithms with Prediction Portfolios

Michael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley, Sergei Vassilvitskii

Comments 24 pages. Appears at NeurIPS 2022

Single Model Uncertainty Estimation via Stochastic Data Centering

Jayaraman J. Thiagarajan, Rushil Anirudh, Vivek Narayanaswamy, Peer-Timo Bremer

Comments Spotlight at NeurIPS 2022

CliMedBERT: A Pre-trained Language Model for Climate and Health-related Text

B. Jalalzadeh Fard, S. A. Hasan, J. E. Bell

Comments 5 pages, 1 figure. Presented at Tackling Climate Change with Machine Learning: workshop at NeurIPS 2022

A POMDP Model for Safe Geological Carbon Sequestration

Anthony Corso, Yizheng Wang, Markus Zechner, Jef Caers, Mykel J. Kochenderfer

Comments Accepted at NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning

Task Discovery: Finding the Tasks that Neural Networks Generalize on

Andrei Atanov, Andrei Filatov, Teresa Yeo, Ajay Sohmshetty, Amir Zamir

Comments NeurIPS 2022, Project page at https://taskdiscovery.epfl.ch

Time-Efficient Reward Learning via Visually Assisted Cluster Ranking

David Zhang, Micah Carroll, Andreea Bobu, Anca Dragan

Comments Presented at the NeurIPS 2022 Human in the Loop Learning (HiLL) Workshop

Denoising Diffusion for Sampling SAT Solutions

Karlis Freivalds, Sergejs Kozlovics

Comments NeurIPS 2022 Workshop on Score-Based Methods

Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models

Vikas Raunak, Matt Post, Arul Menezes

Comments NeurIPS 2022 Workshop on Human Evaluation of Generative Models

Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation

Kristian Georgiev, Samuel B. Hopkins

Comments 39 pages, 2 figures

Journal ref Advances in Neural Information Processing Systems, 2022, https://openreview.net/forum?id=g-OkeNXPy-X

Learning to forecast vegetation greenness at fine resolution over Africa with ConvLSTMs

Claire Robin, Christian Requena-Mesa, Vitus Benson, Lazaro Alonso, Jeran Poehls, Nuno Carvalhais, Markus Reichstein

Comments Tackling Climate Change with Machine Learning: workshop at NeurIPS 2022

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Comments 18 pages, 7 figures, Accepted by Neurips 2022, Spotlight Presentation

Explainable Reinforcement Learning via Model Transforms

Mira Finkelstein, Lucy Liu, Nitsan Levy Schlot, Yoav Kolumbus, David C. Parkes, Jeffrey S. Rosenshein, Sarah Keren

Comments Conference on Neural Information Processing Systems (NeurIPS) 2022

Unsupervised Learning under Latent Label Shift

Manley Roberts, Pranav Mani, Saurabh Garg, Zachary C. Lipton

Comments NeurIPS 2022. Manley Roberts and Pranav Mani contributed equally to this work

Semantic uncertainty intervals for disentangled latent spaces

Swami Sankaranarayanan, Anastasios N. Angelopoulos, Stephen Bates, Yaniv Romano, Phillip Isola

Comments Accepted to NeurIPS 2022. Project page: https://swamiviv.github.io/semantic_uncertainty_intervals/

Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games

Brian Hu Zhang, Tuomas Sandholm

Comments NeurIPS 2022

Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer

Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang

Comments Accepted at NeurIPS 2021. Changes in v3: updated CVRP performance due to more accurate feasibility masks (reduced training time); improved comparison analysis in Table 1 and Section 5; fixed minor typos/inaccuracies in the CPE equation, Figure 6, and other sentences

Attention Bottlenecks for Multimodal Fusion

Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, Chen Sun

Comments Published at NeurIPS 2021. Note this version updates numbers due to a bug in the AudioSet mAP calculation in Table 1 (last row)

BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?

Joel Niklaus, Daniele Giofré

Comments Accepted at ENLSP @ NeurIPS 2022

sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion

Anna Munoz-Farre, Harry Rose, Sera Aylin Cakiroglu

Comments Workshop on Learning from Time Series for Health, 36th Conference on Neural Information Processing Systems (NeurIPS 2022). arXiv admin note: text overlap with arXiv:2202.09318

Multiresolution Textual Inversion

Giannis Daras, Alexandros G. Dimakis

Comments Accepted at NeurIPS 2022 Workshop on Score-Based Methods. 5 pages, 4 Figures, work in progress

Fair Ranking with Noisy Protected Attributes

Anay Mehrotra, Nisheeth K. Vishnoi

Comments Full version of a paper accepted for presentation in NeurIPS 2022

Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders

Ciro Antonio Mami, Andrea Coser, Eric Medvet, Alexander T. P. Boudewijn, Marco Volpe, Michael Whitworth, Borut Svara, Gabriele Sgroi, Daniele Panfilo, Sebastiano Saccani

Comments 8 pages, 2 figures, 2 tables, Synthetic Data 4 ML workshop of the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

WeatherFusionNet: Predicting Precipitation from Satellite Data

Jiří Pihrt, Rudolf Raevskiy, Petr Šimánek, Matej Choma

Comments NeurIPS 2022, Weather4Cast core challenge

HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression

Jiaqi Gu, Ben Keller, Jean Kossaifi, Anima Anandkumar, Brucek Khailany, David Z. Pan

Comments 9 pages. Accepted to NeurIPS ML for System Workshop 2022 (Spotlight)

Geoclidean: Few-Shot Generalization in Euclidean Geometry

Joy Hsu, Jiajun Wu, Noah D. Goodman

Comments To appear at NeurIPS 2022

Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies

Melody Wolk, Andy Applebaum, Camron Dennler, Patrick Dwyer, Marina Moskowitz, Harold Nguyen, Nicole Nichols, Nicole Park, Paul Rachwalski, Frank Rau, Adrian Webster

Comments NeurIPS 2022 Workshop: Reinforcement Learning for Real Life

Learning to Discover and Detect Objects

Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé, Aljoša Ošep

Comments Accepted to NeurIPS 2022, Homepage: https://vlfom.github.io/RNCDL/