# Generalization Bounds on Multi-Kernel Learning with Mixed Datasets

arXiv: https://arxiv.org/abs/2205.07313 · HTML: https://mlsanity.com/paper/2205.07313/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 15 May 2022.

## Builds on (most cited first, 3 of 3)

- [Estimating the Mixing Time of Ergodic Markov Chains](https://mlsanity.com/paper/1902.01224/) (2019)
- [Generalization Error Bounds on Deep Learning with Markov Datasets](https://mlsanity.com/paper/2201.11059/) (2021)
- [Computationally Efficient Estimation of the Spectral Gap of a Markov Chain](https://mlsanity.com/paper/1806.06047/) (2018)

## Built on by (most cited first, 1 of 1)

- [On Rademacher Complexity-based Generalization Bounds for Deep Learning](https://mlsanity.com/paper/2208.04284/) (2022)

## Abstract (arXiv)

This paper presents novel generalization bounds for the multi-kernel learning problem. Motivated by applications in sensor networks and spatial-temporal models, we assume that the dataset is mixed where each sample is taken from a finite pool of Markov chains. Our bounds for learning kernels admit O(√log m) dependency on the number of base kernels and O(1/√n) dependency on the number of training samples. However, some O(1/√n) terms are added to compensate for the dependency among samples compared with existing generalization bounds for multi-kernel learning with i.i.d. datasets.