# Fixing an error in Caponnetto and de Vito (2007)

arXiv: https://arxiv.org/abs/1702.02982 · HTML: https://mlsanity.com/paper/1702.02982/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2017.

## Built on by (most cited first, 3 of 3)

- [Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction](https://mlsanity.com/paper/2105.04544/) (2021)
- [Kernel Ridge Riesz Representers: Generalization, Mis-specification, and the Counterfactual Effective Dimension](https://mlsanity.com/paper/2102.11076/) (2021)
- [Finite-Sample Theory for Fitted Q-Iteration When Actions Are Functions](https://mlsanity.com/paper/2609.36390/) (2026)

## Abstract (arXiv)

The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting. Its proof, however, contains an error in its bound on the effective dimensionality. In this note, we explain the mistake, provide a correct bound, and show that the main theorem remains true.