# Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameters

arXiv: https://arxiv.org/abs/2507.07941 · HTML: https://mlsanity.com/paper/2507.07941/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Nonparametric regression using deep neural networks with ReLU activation function](https://mlsanity.com/paper/1708.06633/) (2017)
- [Quasi-Oracle Estimation of Heterogeneous Treatment Effects](https://mlsanity.com/paper/1712.04912/) (2017)
- [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)
- [Causal machine learning for predicting treatment outcomes](https://mlsanity.com/paper/2410.08770/) (2024)
- [Transfer Learning under High-dimensional Generalized Linear Models](https://mlsanity.com/paper/2105.14328/) (2021)
- [Transfer Learning in Large-scale Gaussian Graphical Models with False Discovery Rate Control](https://mlsanity.com/paper/2010.11037/) (2020)
- [Adaptive and Robust Multi-Task Learning](https://mlsanity.com/paper/2202.05250/) (2022)
- [Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness](https://mlsanity.com/paper/2303.17765/) (2023)
- [Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedure](https://mlsanity.com/paper/2401.12272/) (2024)
- [Minimax optimal approaches to the label shift problem in non-parametric settings](https://mlsanity.com/paper/2003.10443/) (2020)
- [Robust angle-based transfer learning in high dimensions](https://mlsanity.com/paper/2210.12759/) (2022)
- [Heterogeneity-aware and communication-efficient distributed statistical inference](https://mlsanity.com/paper/1912.09623/) (2019)
- [Doubly Robust Augmented Model Accuracy Transfer Inference with High Dimensional Features](https://mlsanity.com/paper/2208.05134/) (2022)
- [Evaluating (weighted) dynamic treatment effects by double machine learning](https://mlsanity.com/paper/2012.00370/) (2020)
- [Machine learning in policy evaluation: new tools for causal inference](https://mlsanity.com/paper/1903.00402/) (2019)
- [Doubly-robust inference and optimality in structure-agnostic models with smoothness](https://mlsanity.com/paper/2405.08525/) (2024)
- [Double/Debiased Machine Learning for Logistic Partially Linear Model](https://mlsanity.com/paper/2009.14461/) (2020)
- [Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits](https://mlsanity.com/paper/2403.03281/) (2024)
- [A Semiparametric Approach to Model Effect Modification](https://mlsanity.com/paper/1804.05373/) (2018)

## Built on by (most cited first, 2 of 2)

- [Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety](https://mlsanity.com/paper/2605.17126/) (2026)
- [Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality](https://mlsanity.com/paper/2605.01907/) (2026)

## Abstract (arXiv)

In the age of large and heterogeneous datasets, the integration of information from diverse sources is essential to improve parameter estimation. Multi-task learning offers a powerful approach by enabling simultaneous learning across related tasks. In this work, we introduce a late fusion framework for multi-task learning with semiparametric models that involve infinite-dimensional nuisance parameters, focusing on applications such as heterogeneous treatment effect estimation across multiple data sources, including electronic health records from different hospitals or clinical trial data. Our framework is two-step: first, initial double machine-learning estimators are obtained through individual task learning; second, these estimators are adaptively aggregated to exploit task similarities while remaining robust to task-specific differences. In particular, the framework avoids individual level data sharing, preserving privacy. Additionally, we propose a novel multi-task learning method for nuisance parameter estimation, which further enhances parameter estimation when nuisance parameters exhibit similarity across tasks. We establish theoretical guarantees for the method, demonstrating faster convergence rates compared to individual task learning when tasks share similar parametric components. Extensive simulations and real data applications complement the theoretical findings of our work while highlight the effectiveness of our framework even in moderate sample sizes.