# Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST)

arXiv: https://arxiv.org/abs/2211.16557 · HTML: https://mlsanity.com/paper/2211.16557/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 58 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Builds on (most cited first, 14 of 14)

- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [The Benefit of Multitask Representation Learning](https://mlsanity.com/paper/1505.06279/) (2015)
- [Provable Meta-Learning of Linear Representations](https://mlsanity.com/paper/2002.11684/) (2020)
- [Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality](https://mlsanity.com/paper/2006.10593/) (2020)
- [Transfer Learning under High-dimensional Generalized Linear Models](https://mlsanity.com/paper/2105.14328/) (2021)
- [Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifier](https://mlsanity.com/paper/1906.02903/) (2019)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach](https://mlsanity.com/paper/2108.12112/) (2021)
- [Adaptive transfer learning](https://mlsanity.com/paper/2106.04455/) (2021)
- [Improving Transferability of Deep Neural Networks](https://mlsanity.com/paper/1807.11459/) (2018)
- [Discussion of "A Gibbs sampler for a class of random convex polytopes"](https://mlsanity.com/paper/2104.02717/) (2021)
- [Turning the information-sharing dial: efficient inference from different data sources](https://mlsanity.com/paper/2207.08886/) (2022)

## Built on by (most cited first, 6 of 6)

- [Multi-modal MRI Translation via Evidential Regression and Distribution Calibration](https://mlsanity.com/paper/2407.07372/) (2024)
- [The ART of Transfer Learning: An Adaptive and Robust Pipeline](https://mlsanity.com/paper/2305.00520/) (2023)
- [Multivariate and Online Transfer Learning with Uncertainty Quantification](https://mlsanity.com/paper/2411.12555/) (2024)
- [Formal Bayesian Transfer Learning via the Total Risk Prior](https://mlsanity.com/paper/2507.23768/) (2025)
- [Invariant Feature Extraction Through Conditional Independence and the Optimal Transport Barycenter Problem: the Gaussian case](https://mlsanity.com/paper/2512.20914/) (2025)
- [Model-agnostic information transfer and fusion for classification with label noise](https://mlsanity.com/paper/2604.25845/) (2026)

## Abstract (arXiv)

Transfer learning uses a data model, trained to make predictions or inferences on data from one population, to make reliable predictions or inferences on data from another population. Most existing transfer learning approaches are based on fine-tuning pre-trained neural network models, and fail to provide crucial uncertainty quantification. We develop a statistical framework for model predictions based on transfer learning, called RECaST. The primary mechanism is a Cauchy random effect that recalibrates a source model to a target population; we mathematically and empirically demonstrate the validity of our RECaST approach for transfer learning between linear models, in the sense that prediction sets will achieve their nominal stated coverage, and we numerically illustrate the method's robustness to asymptotic approximations for nonlinear models. Whereas many existing techniques are built on particular source models, RECaST is agnostic to the choice of source model. For example, our RECaST transfer learning approach can be applied to a continuous or discrete data model with linear or logistic regression, deep neural network architectures, etc. Furthermore, RECaST provides uncertainty quantification for predictions, which is mostly absent in the literature. We examine our method's performance in a simulation study and in an application to real hospital data.