# Challenges in creative generative models for music: a divergence maximization perspective

**Authors:** Axel Chemla--Romeu-Santos, Philippe Esling  
**arXiv:** [2211.08856](https://arxiv.org/abs/2211.08856)  
**Date:** 2022-11-16  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2211.08856v1/

## Key points

- Generative machine learning models have gained interest in creative practices
- Usability and availability of pre-trained models have enabled their use in artistic domains
- Limitations exist in current evaluation methods used by scientists
- Models are still unable to generate content outside of the training dataset domain
- "Challenges in Creative Generative Models for Music: A Divergence Maximization Perspective" proposes a new framework for ML objectives
- The proposed framework aims to address lack of creativity in existing generative models by maximizing divergence between generated outputs and training data while taking into account conditioning variables that contextualize generation
- CC-inspired evaluation method suggested to promote creative output from generative models
- Proposed framework can facilitate better integration of these techniques into artistic domains while promoting more diverse and innovative outputs beyond those defined by training datasets.

## Summary

The development of generative machine learning (ML) models in creative practices has gained significant interest among artists, practitioners, and performers. Recent improvements in the usability and availability of pre-trained models have enabled the use of these techniques in artistic domains. However, the introduction of such techniques has also revealed multiple limitations that escape current evaluation methods used by scientists. Notably, most models are still unable to generate content that lay outside of the domain defined by the training dataset. In this paper titled "Challenges in Creative Generative Models for Music: A Divergence Maximization Perspective," Axel Chemla-Romeu-Santos and Philippe Esling propose an alternative prospective framework starting from a new general formulation of ML objectives. The authors derive this framework to delineate possible implications and solutions that already exist in the ML literature, notably for the audio and musical domain. The proposed framework aims to address the lack of creativity in existing generative models by maximizing divergence between generated outputs and training data while taking into account conditioning variables that contextualize generation. The authors suggest using a CC-inspired evaluation method to promote creative output from generative models. The paper discusses existing relations between generative models and computational creativity, highlighting how their proposed framework could help overcome current limitations faced by generative ML models. By providing a more comprehensive evaluation method for generative models' creative output, this framework can facilitate better integration of these techniques into artistic domains while promoting more diverse and innovative outputs beyond those defined by training datasets. Overall, this paper presents an important contribution towards advancing creative applications of generative ML models while addressing current limitations faced by these techniques in artistic domains.