# Adaptive Data Fusion for Multi-task Non-smooth Optimization

arXiv: https://arxiv.org/abs/2210.12334 · HTML: https://mlsanity.com/paper/2210.12334/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 22 Oct 2022.

## Builds on (most cited first, 7 of 7)

- [Adaptive and Robust Multi-Task Learning](https://mlsanity.com/paper/2202.05250/) (2022)
- [Multivariate Quantile Function Forecaster](https://mlsanity.com/paper/2202.11316/) (2022)
- [First-order Newton-type Estimator for Distributed Estimation and Inference](https://mlsanity.com/paper/1811.11368/) (2018)
- [Data-Pooling in Stochastic Optimization](https://mlsanity.com/paper/1906.00255/) (2019)
- [Distributed inference for quantile regression processes](https://mlsanity.com/paper/1701.06088/) (2017)
- [Efficient Empirical Bayes prediction under check loss using Asymptotic Risk Estimates](https://mlsanity.com/paper/1511.00028/) (2015)
- [Factorisable Multitask Quantile Regression](https://mlsanity.com/paper/1507.03833/) (2015)

## Built on by (most cited first, 3 of 3)

- [On the Uniform Convergence of Subdifferentials in Stochastic Optimization and Learning](https://mlsanity.com/paper/2405.10289/) (2024)
- [Joint Graph Learning and Model Fitting in Laplacian Regularized Stratified Models](https://mlsanity.com/paper/2305.02573/) (2023)
- [Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data](https://mlsanity.com/paper/2505.24413/) (2025)

## Abstract (arXiv)

We study the problem of multi-task non-smooth optimization that arises ubiquitously in statistical learning, decision-making and risk management. We develop a data fusion approach that adaptively leverages commonalities among a large number of objectives to improve sample efficiency while tackling their unknown heterogeneities. We provide sharp statistical guarantees for our approach. Numerical experiments on both synthetic and real data demonstrate significant advantages of our approach over benchmarks.