Learn-By-Calibrating: Using Calibration as a Training Objective
원문 초록
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar to heteroscedastic neural networks that produce variance estimates for each prediction, with the key difference that we do not place a Gaussian prior on the predictions. We propose a novel algorithm that performs simultaneous interval estimation for different calibration levels and effectively leverages the intervals to refine the mean estimates. Our results show that, our approach is consistently superior to existing regularization strategies in deep regression models. Finally, we propose to augment partial dependence plots, a model-agnostic interpretability tool, with expected prediction intervals to reveal interesting dependencies between data and the target.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LLM-Powered CPI Prediction Inference with Online Text Time Series
Model uncertainty quantification using feature confidence sets for outcome excursions
Adapting GT2-FLS for Uncertainty Quantification: A Blueprint Calibration Strategy
NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis Prediction
Conformal Prediction under Levy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
coverforest: Conformal Predictions with Random Forest in Python
토론
이 논문과 연결된 포럼 글이 아직 없습니다.