# Better Latent Spaces for Better Autoencoders

arXiv: https://arxiv.org/abs/2104.08291 · HTML: https://mlsanity.com/paper/2104.08291/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 72 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [VAE with a VampPrior](https://mlsanity.com/paper/1705.07120/) (2017)
- [Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1611.02648/) (2016)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [Anomaly Detection with Density Estimation](https://mlsanity.com/paper/2001.04990/) (2020)
- [Dirichlet Variational Autoencoder](https://mlsanity.com/paper/1901.02739/) (2019)
- [Variational Autoencoders for New Physics Mining at the Large Hadron Collider](https://mlsanity.com/paper/1811.10276/) (2018)
- [Variational Autoencoders for Anomalous Jet Tagging](https://mlsanity.com/paper/2007.01850/) (2020)
- [Simulation Assisted Likelihood-free Anomaly Detection](https://mlsanity.com/paper/2001.05001/) (2020)
- [Novelty Detection Meets Collider Physics](https://mlsanity.com/paper/1807.10261/) (2018)
- [Topological Obstructions to Autoencoding](https://mlsanity.com/paper/2102.08380/) (2021)
- [Bump Hunting in Latent Space](https://mlsanity.com/paper/2103.06595/) (2021)
- [Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quark](https://mlsanity.com/paper/2005.01598/) (2020)
- [Simulation-Assisted Decorrelation for Resonant Anomaly Detection](https://mlsanity.com/paper/2009.02205/) (2020)
- [Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection](https://mlsanity.com/paper/2104.02092/) (2021)
- [Lund jet images from generative and cycle-consistent adversarial networks](https://mlsanity.com/paper/1909.01359/) (2019)
- [Anomaly Awareness](https://mlsanity.com/paper/2007.14462/) (2020)
- [On the Topic of Jets: Disentangling Quarks and Gluons at Colliders](https://mlsanity.com/paper/1802.00008/) (2018)

## Built on by (most cited first, 21 of 21)

- [Machine Learning in the Search for New Fundamental Physics](https://mlsanity.com/paper/2112.03769/) (2021)
- [Autoencoders for unsupervised anomaly detection in high energy physics](https://mlsanity.com/paper/2104.09051/) (2021)
- [Machine Learning for Anomaly Detection in Particle Physics](https://mlsanity.com/paper/2312.14190/) (2023)
- [Deep Generative Models for Detector Signature Simulation: A Taxonomic Review](https://mlsanity.com/paper/2312.09597/) (2023)
- [Challenges for Unsupervised Anomaly Detection in Particle Physics](https://mlsanity.com/paper/2110.06948/) (2021)
- [Online-compatible Unsupervised Non-resonant Anomaly Detection](https://mlsanity.com/paper/2111.06417/) (2021)
- [Anomalies, Representations, and Self-Supervision](https://mlsanity.com/paper/2301.04660/) (2023)
- [Improving new physics searches with diffusion models for event observables and jet constituents](https://mlsanity.com/paper/2312.10130/) (2023)
- [Autoencoders for Semivisible Jet Detection](https://mlsanity.com/paper/2112.02864/) (2021)
- [An Exploration of Learnt Representations of W Jets](https://mlsanity.com/paper/2109.10919/) (2021)
- [IRC-safe Graph Autoencoder for unsupervised anomaly detection](https://mlsanity.com/paper/2204.12231/) (2022)
- [A Detailed Study of Interpretability of Deep Neural Network based Top Taggers](https://mlsanity.com/paper/2210.04371/) (2022)
- [Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging](https://mlsanity.com/paper/2201.07199/) (2022)
- [An autoencoder compression approach for accelerating large-scale inverse problems](https://mlsanity.com/paper/2304.04781/) (2023)
- [Triggering Dark Showers with Conditional Dual Auto-Encoders](https://mlsanity.com/paper/2306.12955/) (2023)
- [Learning symmetries in datasets](https://mlsanity.com/paper/2504.05174/) (2025)
- [Artificial Intelligence and Symmetries: Learning, Encoding, and Discovering Structure in Physical Data](https://mlsanity.com/paper/2602.02351/) (2026)
- [Towards Meaningful Anomaly Detection: The Effect of Counterfactual Explanations on the Investigation of Anomalies in Multivariate Time Series](https://mlsanity.com/paper/2302.03302/) (2023)
- [Drivetrain simulation using variational autoencoders](https://mlsanity.com/paper/2501.17653/) (2025)
- [TRANSIT your events into a new mass: Fast background interpolation for weakly-supervised anomaly searches](https://mlsanity.com/paper/2503.04342/) (2025)
- [Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC](https://mlsanity.com/paper/2610.13437/) (2026)

## Abstract (arXiv)

Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive classifiers from the latent space of (variational) autoencoders, specifically in Gaussian mixture and Dirichlet latent spaces. In particular, the Dirichlet setup solves the problem and improves both the performance and the interpretability of the networks.