Article
Shared architecture, competing objectives: experimental evolution in Drosophila instantiates negative transfer in multi-task learning
2026-06-22
Abstract excerpt
<title>Abstract</title> <p> When competing objectives are optimized through shared components, gains on one can degrade performance on another. Evolutionary biologists call this a fitness trade-off; machine learning researchers call it negative transfer. The structural parallel is rarely made explicit, and the two literatures have developed independently despite describing the same underlying constraint. Here I...
Topics
Open a Topic to create a Post that cites this publication.
Identifiers and source
- Literature Corpus work
- f6157599-c238-580c-ae00-ef4c5a91ce28
- DOI
- 10.21203/rs.3.rs-10084767/v1
