# Tunable Domain Adaptation Using Unfolding

arXiv: https://arxiv.org/abs/2603.26931 · HTML: https://mlsanity.com/paper/2603.26931/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [SpotTune: Transfer Learning through Adaptive Fine-tuning](https://mlsanity.com/paper/1811.08737/) (2018)
- [Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality](https://mlsanity.com/paper/2006.10593/) (2020)
- [Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds](https://mlsanity.com/paper/1808.10038/) (2018)
- [Ada-LISTA: Learned Solvers Adaptive to Varying Models](https://mlsanity.com/paper/2001.08456/) (2020)
- [Hyperparameter Tuning is All You Need for LISTA](https://mlsanity.com/paper/2110.15900/) (2021)
- [Gradual Domain Adaptation: Theory and Algorithms](https://mlsanity.com/paper/2310.13852/) (2023)
- [Transfer Learning for Linear Regression: a Statistical Test of Gain](https://mlsanity.com/paper/2102.09504/) (2021)
- [Sparse Phase Retrieval via Truncated Amplitude Flow](https://mlsanity.com/paper/1611.07641/) (2016)
- [Unfolded Algorithms for Deep Phase Retrieval](https://mlsanity.com/paper/2012.11102/) (2020)
- [Interpretations of Domain Adaptations via Layer Variational Analysis](https://mlsanity.com/paper/2302.01798/) (2023)
- [A Fast and Provable Algorithm for Sparse Phase Retrieval](https://mlsanity.com/paper/2309.02046/) (2023)
- [Representation Transfer Learning for Semiparametric Regression](https://mlsanity.com/paper/2406.13197/) (2024)
- [Algorithm-Induced Prior for Image Restoration](https://mlsanity.com/paper/1602.00715/) (2016)
- [Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding](https://mlsanity.com/paper/2112.10985/) (2021)
- [Unrolled Compressed Blind-Deconvolution](https://mlsanity.com/paper/2209.14165/) (2022)

## Abstract (arXiv)

Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate models per domain, and joint training, which uses a single model for all domains, have significant limitations in flexibility and effectiveness. To address this, we propose two novel domain adaptation methods for regression tasks based on interpretable unrolled networks--deep architectures inspired by iterative optimization algorithms. These models leverage the functional dependence of select tunable parameters on domain variables, enabling controlled adaptation during inference. Our methods include Parametric Tunable-Domain Adaptation (P-TDA), which uses known domain parameters for dynamic tuning, and Data-Driven Tunable-Domain Adaptation (DD-TDA), which infers domain adaptation directly from input data. We validate our approach on compressed sensing problems involving noise-adaptive sparse signal recovery, domain-adaptive gain calibration, and domain-adaptive phase retrieval, demonstrating improved or comparable performance to domain-specific models while surpassing joint training baselines. This work highlights the potential of unrolled networks for effective, interpretable domain adaptation in regression settings.