Minimum-norm interpolants in reproducing kernel Hilbert spaces have risk that can exhibit multiple peaks and valleys as the sample size grows, with peak locations predicted by the scaling d = n^α.
Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong generalization performance for "overfitted" / interpolated classifiers appears to be ubiquitous in high-dimensional data, having been observed in deep networks, kernel machines, boosting and random forests. Their performance is consistently robust even when the data contain large amounts of label noise. Very little theory is available to explain these observations. The vast majority of theoretical analyses of generalization allows for interpolation only when there is little or no label noise. This paper takes a step toward a theoretical foundation for interpolated classifiers by analyzing local interpolating schemes, including geometric simplicial interpolation algorithm and singularly weighted $k$-nearest neighbor schemes. Consistency or near-consistency is proved for these schemes in classification and regression problems. Moreover, the nearest neighbor schemes exhibit optimal rates under some standard statistical assumptions. Finally, this paper suggests a way to explain the phenomenon of adversarial examples, which are seemingly ubiquitous in modern machine learning, and also discusses some connections to kernel machines and random forests in the interpolated regime.
fields
math.ST 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
Minimum-norm interpolants in reproducing kernel Hilbert spaces have risk that can exhibit multiple peaks and valleys as the sample size grows, with peak locations predicted by the scaling d = n^α.