# Amortized Neural Clustering of Time Series based on Statistical Features

arXiv: https://arxiv.org/abs/2605.13128 · HTML: https://mlsanity.com/paper/2605.13128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 59 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows](https://mlsanity.com/paper/1805.07226/) (2018)
- [Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality](https://mlsanity.com/paper/2008.00444/) (2020)
- [Learning Robust Statistics for Simulation-based Inference under Model Misspecification](https://mlsanity.com/paper/2305.15871/) (2023)
- [Bayesian Synthetic Likelihood](https://mlsanity.com/paper/2305.05120/) (2023)
- [Clustering Algorithms: A Comparative Approach](https://mlsanity.com/paper/1612.08388/) (2016)
- [Stop using the elbow criterion for k-means and how to choose the number of clusters instead](https://mlsanity.com/paper/2212.12189/) (2022)
- [Neural network-based clustering using pairwise constraints](https://mlsanity.com/paper/1511.06321/) (2015)
- [Hierarchical Clustering for Smart Meter Electricity Loads based on Quantile Autocovariances](https://mlsanity.com/paper/1911.03336/) (2019)
- [Time series clustering based on prediction accuracy of global forecasting models](https://mlsanity.com/paper/2305.00473/) (2023)
- [Deep Clustering with Self-Supervision using Pairwise Similarities](https://mlsanity.com/paper/2405.03590/) (2024)

## Abstract (arXiv)

This paper introduces an algorithm-agnostic approach to feature-based time series clustering via amortized neural inference. By training neural networks to approximate the optimal partitioning rule from simulated data, the proposed framework reduces reliance on conventional clustering methods, such as K-means, K-medoids, or hierarchical clustering, and their associated objective functions and heuristics. Leveraging statistical features, such as autocorrelations and quantile autocorrelations, the approach learns a data-driven affinity structure from which clustering partitions can be recovered, without requiring explicit prior specification of cluster shapes or structures. In addition, one version of the method can automatically determine the number of clusters, avoiding ad-hoc selection procedures. Comprehensive empirical studies show that the proposed framework achieves competitive or superior clustering accuracy relative to traditional methods, even in challenging scenarios where competing techniques are provided with the true number of clusters. An application to financial time series of stock returns illustrates its practical utility. By reducing the need for algorithm selection and calibration, the proposed framework opens new possibilities for automated, adaptive, and data-driven clustering of temporal data across scientific and industrial domains.