Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm
The Partial Area Under the ROC Curve (PAUC), typically including One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC), measures the average performance of a binary classifier within a specific false positive rate and/or true positive rate interval, which is a widely adopted measure when decis...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The Partial Area Under the ROC Curve (PAUC), typically including One-way
Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC), measures the average
performance of a binary classifier within a specific false positive rate and/or
true positive rate interval, which is a widely adopted measure when decision
constraints must be considered. Consequently, PAUC optimization has naturally
attracted increasing attention in the machine learning community within the
last few years. Nonetheless, most of the existing methods could only optimize
PAUC approximately, leading to inevitable biases that are not controllable.
Fortunately, a recent work presents an unbiased formulation of the PAUC
optimization problem via distributional robust optimization. However, it is
based on the pair-wise formulation of AUC, which suffers from the limited
scalability w.r.t. sample size and a slow convergence rate, especially for
TPAUC. To address this issue, we present a simpler reformulation of the problem
in an asymptotically unbiased and instance-wise manner. For both OPAUC and
TPAUC, we come to a nonconvex strongly concave minimax regularized problem of
instance-wise functions. On top of this, we employ an efficient solver enjoys a
linear per-iteration computational complexity w.r.t. the sample size and a
time-complexity of $O(\epsilon^{-1/3})$ to reach a $\epsilon$ stationary point.
Furthermore, we find that the minimax reformulation also facilitates the
theoretical analysis of generalization error as a byproduct. Compared with the
existing results, we present new error bounds that are much easier to prove and
could deal with hypotheses with real-valued outputs. Finally, extensive
experiments on several benchmark datasets demonstrate the effectiveness of our
method. |
---|---|
DOI: | 10.48550/arxiv.2210.03967 |