Evolutionary Retrofitting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Videau, Mathurin, Zameshina, Mariia, Leite, Alessandro, Najman, Laurent, Schoenauer, Marc, Teytaud, Olivier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908651659198464
author Videau, Mathurin
Zameshina, Mariia
Leite, Alessandro
Najman, Laurent
Schoenauer, Marc
Teytaud, Olivier
author_facet Videau, Mathurin
Zameshina, Mariia
Leite, Alessandro
Najman, Laurent
Schoenauer, Marc
Teytaud, Olivier
contents AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via Latent Diffusion Models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11330
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evolutionary Retrofitting
Videau, Mathurin
Zameshina, Mariia
Leite, Alessandro
Najman, Laurent
Schoenauer, Marc
Teytaud, Olivier
Machine Learning
Neural and Evolutionary Computing
Optimization and Control
AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via Latent Diffusion Models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.
title Evolutionary Retrofitting
topic Machine Learning
Neural and Evolutionary Computing
Optimization and Control
url https://arxiv.org/abs/2410.11330