# Convex Learning of Multiple Tasks and their Structure

arXiv: https://arxiv.org/abs/1504.03101 · HTML: https://mlsanity.com/paper/1504.03101/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2015.

## Built on by (most cited first, 13 of 13)

- [Segmentation-grounded Scene Graph Generation](https://mlsanity.com/paper/2104.14207/) (2021)
- [Average gradient outer product as a mechanism for deep neural collapse](https://mlsanity.com/paper/2402.13728/) (2024)
- [Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance](https://mlsanity.com/paper/2410.01109/) (2024)
- [Entangled Kernels -- Beyond Separability](https://mlsanity.com/paper/2101.05514/) (2021)
- [Nonparametric Teaching for Multiple Learners](https://mlsanity.com/paper/2311.10318/) (2023)
- [Cross-Task Consistency Learning Framework for Multi-Task Learning](https://mlsanity.com/paper/2111.14122/) (2021)
- [PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent](https://mlsanity.com/paper/2202.00531/) (2022)
- [AdaTask: Adaptive Multitask Online Learning](https://mlsanity.com/paper/2205.15802/) (2022)
- [Multi-Task Learning with Prior Information](https://mlsanity.com/paper/2301.01572/) (2023)
- [Invex Programs: First Order Algorithms and Their Convergence](https://mlsanity.com/paper/2307.04456/) (2023)
- [Meta-learning of shared linear representations beyond well-specified linear regression](https://mlsanity.com/paper/2501.18975/) (2025)
- [Bayesian Kernel Regression for Functional Data](https://mlsanity.com/paper/2503.13676/) (2025)
- [Cascaded Transfer: Learning Many Tasks under Budget Constraints](https://mlsanity.com/paper/2601.21513/) (2026)

## Abstract (arXiv)

Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks structure in the learning problem.We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.