mlsanityData to 7 Oct 2026

Better Latent Spaces for Better Autoencoders

arXiv 2104.08291 ↗First posted 16 Apr 2021hep-ph cs.LGcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 18 of its 72 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

18 of 72 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017VAE with a VampPriorcited by 247
  3. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  4. 2017Autoencoding Variational Inference For Topic Modelscited by 168
  5. 2020Anomaly Detection with Density Estimationcited by 71
  6. 2019Dirichlet Variational Autoencodercited by 43
  7. 2018Variational Autoencoders for New Physics Mining at the Large Hadron Collidercited by 40
  8. 2020Variational Autoencoders for Anomalous Jet Taggingcited by 33
  9. 2020Simulation Assisted Likelihood-free Anomaly Detectioncited by 27
  10. 2018Novelty Detection Meets Collider Physicscited by 20
  11. 2021Topological Obstructions to Autoencodingcited by 20
  12. 2021Bump Hunting in Latent Spacecited by 19
6 more
  1. 2020Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quarkcited by 18
  2. 2020Simulation-Assisted Decorrelation for Resonant Anomaly Detectioncited by 13
  3. 2021Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detectioncited by 13
  4. 2019Lund jet images from generative and cycle-consistent adversarial networkscited by 11
  5. 2020Anomaly Awarenesscited by 10
  6. 2018On the Topic of Jets: Disentangling Quarks and Gluons at Colliderscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 3; 2023: 7; 2024: 0; 2025: 3; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021Machine Learning in the Search for New Fundamental Physicscited by 50
  2. 2021Autoencoders for unsupervised anomaly detection in high energy physicscited by 32
  3. 2023Machine Learning for Anomaly Detection in Particle Physicscited by 29
  4. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  5. 2021Challenges for Unsupervised Anomaly Detection in Particle Physicscited by 16
  6. 2021Online-compatible Unsupervised Non-resonant Anomaly Detectioncited by 15
  7. 2023Anomalies, Representations, and Self-Supervisioncited by 10
  8. 2023Improving new physics searches with diffusion models for event observables and jet constituentscited by 10
  9. 2021Autoencoders for Semivisible Jet Detectioncited by 9
  10. 2021An Exploration of Learnt Representations of W Jetscited by 8
  11. 2022IRC-safe Graph Autoencoder for unsupervised anomaly detectioncited by 8
  12. 2022A Detailed Study of Interpretability of Deep Neural Network based Top Taggerscited by 6
8 more
  1. 2022Invariant Representation Driven Neural Classifier for Anti-QCD Jet Taggingcited by 4
  2. 2023An autoencoder compression approach for accelerating large-scale inverse problemscited by 1
  3. 2023Triggering Dark Showers with Conditional Dual Auto-Encoderscited by 1
  4. 2025Learning symmetries in datasetscited by 1
  5. 2026Artificial Intelligence and Symmetries: Learning, Encoding, and Discovering Structure in Physical Datacited by 1
  6. 2023Towards Meaningful Anomaly Detection: The Effect of Counterfactual Explanations on the Investigation of Anomalies in Multivariate Time Seriescited by 0
  7. 2025Drivetrain simulation using variational autoencoderscited by 0
  8. 2025TRANSIT your events into a new mass: Fast background interpolation for weakly-supervised anomaly searchescited by 0