# Hyperparameter Learning for Conditional Kernel Mean Embeddings with Rademacher Complexity Bounds

arXiv: https://arxiv.org/abs/1809.00175 · HTML: https://mlsanity.com/paper/1809.00175/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2018.

## Built on by (most cited first, 4 of 4)

- [Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes](https://mlsanity.com/paper/2109.03582/) (2021)
- [BayesIMP: Uncertainty Quantification for Causal Data Fusion](https://mlsanity.com/paper/2106.03477/) (2021)
- [Safe reinforcement learning in uncertain contexts](https://mlsanity.com/paper/2401.05876/) (2024)
- [Non-Linear Spectral Dimensionality Reduction Under Uncertainty](https://mlsanity.com/paper/2202.04678/) (2022)

## Abstract (arXiv)

Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space. While they provide a flexible and powerful framework for probabilistic inference, their performance is highly dependent on the choice of kernel and regularization hyperparameters. Nevertheless, current hyperparameter tuning methods predominantly rely on expensive cross validation or heuristics that is not optimized for the inference task. For conditional kernel mean embeddings with categorical targets and arbitrary inputs, we propose a hyperparameter learning framework based on Rademacher complexity bounds to prevent overfitting by balancing data fit against model complexity. Our approach only requires batch updates, allowing scalable kernel hyperparameter tuning without invoking kernel approximations. Experiments demonstrate that our learning framework outperforms competing methods, and can be further extended to incorporate and learn deep neural network weights to improve generalization.