Predictive Value Generalization Bounds
In this paper, we study a bi-criterion framework for assessing scoring functions in the context of binary classification. The positive and negative predictive values (ppv and npv, respectively) are conditional probabilities of the true label matching a classifier's predicted label. The usual classification error rate is a linear combination of these probabilities, and therefore, concentration inequalities for the error rate do not yield confidence intervals for the two separate predictive values. We study generalization properties of scoring functions with respect to predictive values by deriving new distribution-free large deviation and uniform convergence bounds. The latter bound is stated in terms of a measure of function class complexity that we call the order coefficient; we relate this combinatorial quantity to the VC-subgraph dimension.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationGeneral ClassificationGeneralization BoundsSimilar Papers 제목 키워드 기반
Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms
Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical…
BIG-bench Machine LearningSingular Bayesian Neural Networks
Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors. We argue this cost is often unnecessary, particularly when weight matrices exhibit fast …
Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses
The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence. Previ…
Generalization BoundsvalidPAC$^m$-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime
The Bayesian posterior minimizes the "inferential risk" which itself bounds the "predictive risk". This bound is tight when the likelihood and prior are well-specified. However since misspecification induces a gap, the B…
Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probabil…