%0 Conference Paper %1 guo2017calibration %A Guo, Chuan %A Pleiss, Geoff %A Sun, Yu %A Weinberger, Kilian Q. %B roceedings of the 34th International Conference on Machine Learning %D 2017 %I PMLR %K calibration learning machine ml network neural %P 1321-1330 %T On Calibration of Modern Neural Networks %U http://proceedings.mlr.press/v70/guo17a.html %V 70 %X Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling – a single-parameter variant of Platt Scaling – is surprisingly effective at calibrating predictions.

@inproceedings{guo2017calibration, abstract = {Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling – a single-parameter variant of Platt Scaling – is surprisingly effective at calibrating predictions. }, added-at = {2023-11-03T13:23:31.000+0100}, author = {Guo, Chuan and Pleiss, Geoff and Sun, Yu and Weinberger, Kilian Q.}, biburl = {https://www.bibsonomy.org/bibtex/24f83b229e504dc3903ed15e15f7acd6c/jaeschke}, booktitle = {roceedings of the 34th International Conference on Machine Learning}, description = {On Calibration of Modern Neural Networks}, interhash = {315c62001aeac75c9ddacc6a8afa7f8e}, intrahash = {4f83b229e504dc3903ed15e15f7acd6c}, issn = {2640-3498}, keywords = {calibration learning machine ml network neural}, pages = {1321-1330}, publisher = {PMLR}, timestamp = {2023-11-03T13:23:44.000+0100}, title = {On Calibration of Modern Neural Networks}, url = {http://proceedings.mlr.press/v70/guo17a.html}, volume = 70, year = 2017 }