Adaptive, Distribution-Free Prediction Intervals for Deep Networks
원문 초록
The machine learning literature contains several constructions for prediction intervals that are intuitively reasonable but ultimately ad-hoc in that they do not come with provable performance guarantees. We present methods from the statistics literature that can be used efficiently with neural networks under minimal assumptions with guaranteed performance. We propose a neural network that outputs three values instead of a single point estimate and optimizes a loss function motivated by the standard quantile regression loss. We provide two prediction interval methods with finite sample coverage guarantees solely under the assumption that the observations are independent and identically distributed. The first method leverages the conformal inference framework and provides average coverage. The second method provides a new, stronger guarantee by conditioning on the observed data. Lastly, our loss function does not compromise the predictive accuracy of the network like other prediction interval methods. We demonstrate the ease of use of our procedures as well as its improvements over other methods on both simulated and real data. As most deep networks can easily be modified by our method to output predictions with valid prediction intervals, its use should become standard practice, much like reporting standard errors along with mean estimates.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Optimal Conformal Prediction under Epistemic Uncertainty
Uncertainty Quantification in SVM prediction
Foundation models for time series forecasting: Application in conformal prediction
A Wireless Foundation Model for Multi-Task Prediction
Valid Selection among Conformal Sets
On the relationship between prediction intervals, tests of sharp nulls and inference on realized treatment effects in settings with few treated units
토론
이 논문과 연결된 포럼 글이 아직 없습니다.