# Autonomy-Aware Clustering: When Local Decisions Supersede Global Prescriptions

arXiv: https://arxiv.org/abs/2509.25775 · HTML: https://mlsanity.com/paper/2509.25775/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Probabilistic Latent Semantic Analysis](https://mlsanity.com/paper/1301.6705/) (2013)
- [Better Algorithms for Individually Fair k-Clustering](https://mlsanity.com/paper/2106.12150/) (2021)
- [CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition](https://mlsanity.com/paper/2101.07042/) (2021)
- [Approximation algorithms for stochastic clustering](https://mlsanity.com/paper/1809.02271/) (2018)
- [Parameterized MDPs and Reinforcement Learning Problems -- A Maximum Entropy Principle Based Framework](https://mlsanity.com/paper/2006.09646/) (2020)
- [Online Deterministic Annealing for Classification and Clustering](https://mlsanity.com/paper/2102.05836/) (2021)
- [Stochastic Optimization and Learning for Two-Stage Supplier Problems](https://mlsanity.com/paper/2008.03325/) (2020)
- [Orthogonal Nonnegative Matrix Factorization with Sparsity Constraints](https://mlsanity.com/paper/2210.02672/) (2022)

## Abstract (arXiv)

Clustering arises in a wide range of problem formulations, yet most existing approaches assume that the entities under clustering are passive and strictly conform to their assigned groups. In reality, entities often exhibit local autonomy, overriding prescribed associations in ways not fully captured by feature representations. Such autonomy can substantially reshape clustering outcomes -- altering cluster compositions, geometry, and cardinality -- with significant downstream effects on inference and decision-making. We introduce autonomy-aware clustering, a reinforcement learning (RL) framework that learns and accounts for the influence of local autonomy without requiring prior knowledge of its form. Our approach integrates RL with a Deterministic Annealing (DA) procedure, where, to determine underlying clusters, DA naturally promotes exploration in early stages of annealing and transitions to exploitation later. We also show that the annealing procedure exhibits phase transitions that enable design of efficient annealing schedules. To further enhance adaptability, we propose the Adaptive Distance Estimation Network (ADEN), a transformer-based attention model that learns dependencies between entities and cluster representatives within the RL loop, accommodates variable-sized inputs and outputs, and enables knowledge transfer across diverse problem instances. Empirical results show that our framework closely aligns with underlying data dynamics: even without explicit autonomy models, it achieves solutions close to the ground truth (gap ~3-4%), whereas ignoring autonomy leads to substantially larger gaps (~35-40%). The code and data are publicly available at https://github.com/salar96/AutonomyAwareClustering.