# Multi-task and Lifelong Learning of Kernels

arXiv: https://arxiv.org/abs/1602.06531 · HTML: https://mlsanity.com/paper/1602.06531/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2016.

## Built on by (most cited first, 7 of 7)

- [Kernel Continual Learning](https://mlsanity.com/paper/2107.05757/) (2021)
- [Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning](https://mlsanity.com/paper/2408.16939/) (2024)
- [On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure](https://mlsanity.com/paper/2211.15129/) (2022)
- [Information-Theoretic Generalization Bounds of Replay-based Continual Learning](https://mlsanity.com/paper/2507.12043/) (2025)
- [On regret bounds for continual single-index learning](https://mlsanity.com/paper/2102.12961/) (2021)
- [Sharper Risk Bound for Multi-Task Learning with Multi-Graph Dependent Data](https://mlsanity.com/paper/2502.18167/) (2025)
- [Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure](https://mlsanity.com/paper/2511.01847/) (2025)

## Abstract (arXiv)

We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.