# Multi-task learning on the edge: cost-efficiency and theoretical optimality

arXiv: https://arxiv.org/abs/2110.04639 · HTML: https://mlsanity.com/paper/2110.04639/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 12 references that are in the map.
- First posted on arXiv 9 Oct 2021.

## Builds on (most cited first, 1 of 1)

- [Challenges and Opportunities in Edge Computing](https://mlsanity.com/paper/1609.01967/) (2016)

## Built on by (most cited first, 1 of 1)

- [On Steering Multi-Annotations per Sample for Multi-Task Learning](https://mlsanity.com/paper/2203.02946/) (2022)

## Abstract (arXiv)

This article proposes a distributed multi-task learning (MTL) algorithm based on supervised principal component analysis (SPCA) which is: (i) theoretically optimal for Gaussian mixtures, (ii) computationally cheap and scalable. Supporting experiments on synthetic and real benchmark data demonstrate that significant energy gains can be obtained with no performance loss.