Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

6 June 2019

Balaji Lakshminarayanan

Jasper Snoek

UQCV

ArXiv PDF HTML

Papers citing "Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift"

50 / 1,042 papers shown

Title
KL Regularized Normalization Framework for Low Resource Tasks Neeraj Kumar Ankur Narang Brejesh Lall 31 1 0 21 Dec 2022
Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning R. Hebbalaguppe Rishabh Patra T. Dash Gautam M. Shroff L. Vig 22 14 0 20 Dec 2022
Bayesian posterior approximation with stochastic ensembles Oleksandr Balabanov Bernhard Mehlig Hampus Linander BDL UQCV 29 5 0 15 Dec 2022
Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls Stephan Thaler Gregor Doehner Julija Zavadlav 40 21 0 15 Dec 2022
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation Wenyu Zhang Li Shen Chuan-Sheng Foo TTA AI4CE 39 15 0 15 Dec 2022
Uncertainty Quantification for Deep Neural Networks: An Empirical Comparison and Usage Guidelines Michael Weiss Paolo Tonella BDL UQCV 30 11 0 14 Dec 2022
An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty Zhijie Wang Yuheng Huang Lei Ma Haruki Yokoyama Susumu Tokumoto Kazuki Munakata 29 4 0 13 Dec 2022
Efficient Bayesian Uncertainty Estimation for nnU-Net Yidong Zhao Changchun Yang Artur M. Schweidtmann Qian Tao UQCV BDL 27 20 0 12 Dec 2022
Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization Neslihan Kose R. Krishnan Akash Dhamasia Omesh Tickoo Michael Paulitsch 32 1 0 09 Dec 2022
PØDA: Prompt-driven Zero-shot Domain Adaptation Mohammad Fahes Tuan-Hung Vu Andrei Bursuc Patrick Pérez Raoul de Charette VLM 40 47 0 06 Dec 2022
A Learning Based Hypothesis Test for Harmful Covariate Shift T. Ginsberg Zhongyuan Liang Rahul G. Krishnan 16 11 0 06 Dec 2022
Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS Gary Tom Riley J. Hickman Aniket N. Zinzuwadia A. Mohajeri Benjamín Sánchez-Lengeling A. Aspuru‐Guzik 21 16 0 03 Dec 2022
Understanding the Robustness of Multi-Exit Models under Common Corruptions Akshay Mehra Skyler Seto Navdeep Jaitly B. Theobald AAML 24 3 0 03 Dec 2022
Investigating Deep Learning Model Calibration for Classification Problems in Mechanics S. Mohammadzadeh Peerasait Prachaseree Emma Lejeune AI4CE 34 2 0 01 Dec 2022
A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification Paul F. Jaeger Carsten T. Lüth Lukas Klein Till J. Bungert UQCV 30 35 0 28 Nov 2022
Class Adaptive Network Calibration Bingyuan Liu Jérôme Rony Adrian Galdran Jose Dolz Ismail Ben Ayed 48 8 0 28 Nov 2022
Looking at the posterior: accuracy and uncertainty of neural-network predictions Hampus Linander Oleksandr Balabanov Henry Yang Bernhard Mehlig UQCV UD BDL 43 2 0 26 Nov 2022
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification Xing Yan Yonghua Su Wenxuan Ma UQCV 44 1 0 26 Nov 2022
Improving Multi-task Learning via Seeking Task-based Flat Regions Hoang Phan Lam C. Tran Ngoc N. Tran Nhat Ho Dinh Q. Phung Trung Le 38 11 0 24 Nov 2022
MP-GELU Bayesian Neural Networks: Moment Propagation by GELU Nonlinearity Yuki Hirayama Sinya Takamaeda-Yamazaki BDL 32 0 0 24 Nov 2022
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks Neil Band Tim G. J. Rudner Qixuan Feng Angelos Filos Zachary Nado Michael W. Dusenberry Ghassen Jerfel Dustin Tran Y. Gal OOD UQCV BDL 29 50 0 23 Nov 2022
AdaFocal: Calibration-aware Adaptive Focal Loss Arindam Ghosh Thomas Schaaf Matthew R. Gormley FedML UQCV 34 25 0 21 Nov 2022
Layer-Stack Temperature Scaling Amr Khalifa Michael C. Mozer Hanie Sedghi Behnam Neyshabur Ibrahim M. Alabdulmohsin 81 2 0 18 Nov 2022
Weighted Ensemble Self-Supervised Learning Yangjun Ruan Saurabh Singh Warren Morningstar Alexander A. Alemi Sergey Ioffe Ian S. Fischer Joshua V. Dillon FedML 29 15 0 18 Nov 2022
Introduction and Exemplars of Uncertainty Decomposition Shuo Chen UD UQCV PER 35 0 0 17 Nov 2022
Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction Masha Itkina Mykel J. Kochenderfer EDL UQCV 26 26 0 16 Nov 2022
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks Tommaso Salvatori Yuhang Song Yordan Yordanov Beren Millidge Zheng R. Xu Lei Sha Cornelius Emde Rafal Bogacz Thomas Lukasiewicz 36 10 0 16 Nov 2022
Calibrated Interpretation: Confidence Estimation in Semantic Parsing Elias Stengel-Eskin Benjamin Van Durme UQLM 41 24 0 14 Nov 2022
Accurate and Reliable Methods for 5G UAV Jamming Identification With Calibrated Uncertainty Hamed Farkhari Joseanne Viana P. Sebastião L. M. Campos Luís Bernardo R. Dinis Sarang Kahvazadeh UQCV 24 2 0 05 Nov 2022
Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS Rishabh Singh José C. Príncipe UQCV 39 3 0 03 Nov 2022
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks Sadegh Mahdavi Kevin Swersky Thomas Kipf Milad Hashemi Christos Thrampoulidis Renjie Liao LRM OOD NAI 57 25 0 01 Nov 2022
Behavioral Intention Prediction in Driving Scenes: A Survey Jianwu Fang Fan Wang Jianru Xue Tat-Seng Chua 59 44 0 01 Nov 2022
A Close Look into the Calibration of Pre-trained Language Models Yangyi Chen Lifan Yuan Yuchen Zhang Zhiyuan Liu Heng Ji 40 44 0 31 Oct 2022
Unsafe's Betrayal: Abusing Unsafe Rust in Binary Reverse Engineering via Machine Learning Sangdon Park Xiang Cheng Taesoo Kim 43 1 0 31 Oct 2022
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms Vincent Plassier Alain Durmus Eric Moulines FedML 21 6 0 31 Oct 2022
A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs Hans Hao-Hsun Hsu Yuesong Shen Daniel Cremers 34 7 0 27 Oct 2022
Revisiting Softmax for Uncertainty Approximation in Text Classification Andreas Nugaard Holm Dustin Wright Isabelle Augenstein BDL UQCV 24 9 0 25 Oct 2022
MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling Julius Ott Lorenzo Servadei Jose A. Arjona-Medina E. Rinaldi Gianfranco Mauro Daniela Sanchez Lopera Michael Stephan Thomas Stadelmayer Avik Santra Robert Wille 28 0 0 24 Oct 2022
Bridging Machine Learning and Sciences: Opportunities and Challenges Taoli Cheng UQCV OOD AI4CE 27 2 0 24 Oct 2022
GFlowOut: Dropout with Generative Flow Networks Dianbo Liu Moksh Jain Bonaventure F. P. Dossou Qianli Shen Salem Lahlou ... Dinghuai Zhang N. Hassen Xu Ji Kenji Kawaguchi Yoshua Bengio UQCV BDL OOD 33 20 0 24 Oct 2022
Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition Sebastian G. Gruber Florian Buettner PER UQCV UD 218 11 0 21 Oct 2022
Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity Dennis Ulmer J. Frellsen Christian Hardmeier 200 22 0 20 Oct 2022
Uncertainty estimation for out-of-distribution detection in computational histopathology Lea Goetz OOD 32 0 0 18 Oct 2022
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel Seijin Kobayashi Pau Vilimelis Aceituno J. Oswald UQCV 29 2 0 18 Oct 2022
Packed-Ensembles for Efficient Uncertainty Estimation Olivier Laurent Adrien Lafage Enzo Tartaglione Geoffrey Daniel Jean-Marc Martinez Andrei Bursuc Gianni Franchi OODD 46 32 0 17 Oct 2022
Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning Jifeng Hu Yanchao Sun Hechang Chen Sili Huang Haiyin Piao Yi-Ju Chang Lichao Sun 25 5 0 14 Oct 2022
Deep Combinatorial Aggregation Yuesong Shen Daniel Cremers OOD UQCV 19 4 0 12 Oct 2022
Quantifying Uncertainty with Probabilistic Machine Learning Modeling in Wireless Sensing Amit Kachroo Sai Prashanth Chinnapalli 23 0 0 12 Oct 2022
Efficient Bayesian Updates for Deep Learning via Laplace Approximations Denis Huseljic M. Herde Lukas Rauch Paul Hahn Zhixin Huang D. Kottke S. Vogt Bernhard Sick BDL 21 0 0 12 Oct 2022
Robust Models are less Over-Confident Julia Grabinski Paul Gavrikov J. Keuper M. Keuper AAML 36 24 0 12 Oct 2022