PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

2019-12-31 · ICLR 2020 1 · Sangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee

We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem.

📄 PDF Abstract BibTeX arXiv:2001.00106

Code (2)

sangdon/PAC-confidence-set 공식 구현 pytorch

leoandeol/cods pytorch

Tasks

Generalization BoundsLearning TheoryObject Tracking reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Visual Object Tracking

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Batch Normalization 설명 없음

Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Kaiming Initialization 설명 없음

Confidence-Calibrated Face and Kinship Verification

2022-10-25 · Min Xu, Ximiao Zhang, Xiuzhuang Zhou

In this paper, we investigate the problem of prediction confidence in face and kinship verification. Most existing face and kinship verification methods focus on accuracy performance while ignoring confidence estimation …

Kinship Verification

Effective Confidence Region Prediction Using Probability Forecasters

2024-05-24 · David Lindsay, Sian Lindsay

Confidence region prediction is a practically useful extension to the commonly studied pattern recognition problem. Instead of predicting a single label, the constraint is relaxed to allow prediction of a subset of label…

Prediction

Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning

2022-12-20 · Ramya Hebbalaguppe, Rishabh Patra, Tirtharaj Dash, Gautam Shroff 외

Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the pro…

image-classification Image Classification

Calibrated and Efficient Sampling-Free Confidence Estimation for LiDAR Scene Semantic Segmentation

2024-11-18 · Hanieh Shojaei Miandashti, Qianqian Zou, Claus Brenner

Reliable deep learning models require not only accurate predictions but also well-calibrated confidence estimates to ensure dependable uncertainty estimation. This is crucial in safety-critical applications like autonomo…

Autonomous Driving LIDAR Semantic Segmentation Scene Understanding Segmentation+1

Uncertainty quantification in automated valuation models with spatially weighted conformal prediction

2023-12-11 · Anders Hjort, Gudmund Horn Hermansen, Johan Pensar, Jonathan P. Williams

Non-parametric machine learning models, such as random forests and gradient boosted trees, are frequently used to estimate house prices due to their predictive accuracy, but a main drawback of such methods is their limit…

Conformal Prediction Uncertainty Quantification