Population-Based Evolution Optimizes a Meta-Learning Objective · HackerPapers discussions

Population-Based Evolution Optimizes a Meta-Learning Objective — HN submission

Fri, 22 Dec 2023 04:21:01 GMT

Population-Based Evolution Optimizes a Meta-Learning Objective

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Population-Based Evolution Optimizes a Meta-Learning Objective — mentioned by kristjansson

Fri, 22 Dec 2023 03:45:04 GMT

Agreed. The paper[0] it's purporting to review is interesting enough, but TFA makes some pretty confused statements about both EAs and metalearning. [0]: https://arxiv.org/abs/2103.06435

Paper and discussion history. A mention is not an endorsement.

Population-Based Evolution Optimizes a Meta-Learning Objective — mentioned by markisus

Fri, 22 Dec 2023 03:21:58 GMT

The referenced paper [1] invents a version of evolutionary algorithm where each gene is associated with a target "population ratio" which is modulated upwards or downwards by that gene's performance, and ultimately decides how many offspring that gene will have. The population ratio is not really a ratio. It's just a float that represents the fiction that a particular genome represents a population of identical clones. A gene is deleted only if its population ratio falls below 0.0001. In this way, the culling decision is softened so that doing poorly on one round of fitness evaluation does…

Paper and discussion history. A mention is not an endorsement.