# Regularized GLISp for sensor-guided human-in-the-loop optimization

arXiv: https://arxiv.org/abs/2511.04751 · HTML: https://mlsanity.com/paper/2511.04751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Safe Controller Optimization for Quadrotors with Gaussian Processes](https://mlsanity.com/paper/1509.01066/) (2015)
- [Preferential Bayesian Optimization](https://mlsanity.com/paper/1704.03651/) (2017)
- [Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses](https://mlsanity.com/paper/2306.13104/) (2023)
- [Efficient Human-in-the-Loop Optimization via Priors Learned from User Models](https://mlsanity.com/paper/2510.07754/) (2025)
- [Human-in-the-loop: Real-time Preference Optimization](https://mlsanity.com/paper/2506.02225/) (2025)

## Abstract (arXiv)

Human-in-the-loop calibration is often addressed via preference-based optimization, where algorithms learn from pairwise comparisons rather than explicit cost evaluations. While effective, methods such as Preferential Bayesian Optimization or Global optimization based on active preference learning with radial basis functions (GLISp) treat the system as a black box and ignore informative sensor measurements. In this work, we introduce a sensor-guided regularized extension of GLISp that integrates measurable descriptors into the preference-learning loop through a physics-informed hypothesis function and a least-squares regularization term. This injects grey-box structure, combining subjective feedback with quantitative sensor information while preserving the flexibility of preference-based search. Numerical evaluations on an analytical benchmark and on a human-in-the-loop vehicle suspension tuning task show faster convergence and superior final solutions compared to baseline GLISp.