Hellström, Fredrik; Guedj, Benjamin; (2024) Comparing Comparators in Generalization Bounds. In: Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen, (eds.) Proceedings of The 27th International Conference on Artificial Intelligence and Statistics. (pp. pp. 73-81). PMLR (Proceedings of Machine Learning Research)

Preview

PDF hellstrom24a.pdf - Published Version Download (932kB) | Preview

Abstract

We derive generic information-theoretic and PAC-Bayesian generalization bounds involving an arbitrary convex comparator function, which measures the discrepancy between the training loss and the population loss. The bounds hold under the assumption that the cumulant-generating function (CGF) of the comparator is upper-bounded by the corresponding CGF within a family of bounding distributions. We show that the tightest possible bound is obtained with the comparator being the convex conjugate of the CGF of the bounding distribution, also known as the Cramér function. This conclusion applies more broadly to generalization bounds with a similar structure. This confirms the near-optimality of known bounds for bounded and sub-Gaussian losses and leads to novel bounds under other bounding distributions.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item