# Theoretical Guarantees of Transfer Learning

arXiv: https://arxiv.org/abs/1810.05986 · HTML: https://mlsanity.com/paper/1810.05986/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2018.

## Built on by (most cited first, 5 of 5)

- [Learning Algorithm Generalization Error Bounds via Auxiliary Distributions](https://mlsanity.com/paper/2210.00483/) (2022)
- [Unsupervised Non-transferable Text Classification](https://mlsanity.com/paper/2210.12651/) (2022)
- [SHiFT: An Efficient, Flexible Search Engine for Transfer Learning](https://mlsanity.com/paper/2204.01457/) (2022)
- [Extracting Global Dynamics of Loss Landscape in Deep Learning Models](https://mlsanity.com/paper/2106.07683/) (2021)
- [Unsupervised Domain Adaptation with Deep Neural-Network](https://mlsanity.com/paper/2307.05601/) (2023)

## Abstract (arXiv)

Transfer learning has been proven effective when within-target labeled data is scarce. A lot of works have developed successful algorithms and empirically observed positive transfer effect that improves target generalization error using source knowledge. However, theoretical analysis of transfer learning is more challenging due to the nature of the problem and thus is less studied. In this report, we do a survey of theoretical works in transfer learning and summarize key theoretical guarantees that prove the effectiveness of transfer learning. The theoretical bounds are derived using model complexity and learning algorithm stability. As we should see, these works exhibit a trade-off between tight bounds and restrictive assumptions. Moreover, we also prove a new generalization bound for the multi-source transfer learning problem using the VC-theory, which is more informative than the one proved in previous work.