mlsanityData to 7 Oct 2026

Hybrid Models with Deep and Invertible Features

arXiv 1902.02767 ↗First posted 7 Feb 2019cs.LG stat.MLcited by 41

Not on the map. Why?

Abstract (arXiv)

We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets | features), the predictive distribution, can be computed exactly in a single feed-forward pass. We show that our hybrid model, despite the invertibility constraints, achieves similar accuracy to purely predictive models. Moreover the generative component remains a good model of the input features despite the hybrid optimization objective. This offers additional capabilities such as detection of out-of-distribution inputs and enabling semi-supervised learning. The availability of the exact joint density p(targets, features) also allows us to compute many quantities readily, making our hybrid model a useful building block for downstream applications of probabilistic deep learning.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 7; 2024: 6; 2025: 4; 2026: 1.

41 papers.

Sort:

By area:

  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  2. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  3. 2021Machine Learning with a Reject Option: A surveycited by 107
  4. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  5. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  6. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  7. 2022Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Modelcited by 58
  8. 2021Densely connected normalizing flowscited by 49
  9. 2021Featurized Density Ratio Estimationcited by 33
  10. 2022Universal approximation property of invertible neural networkscited by 30
  11. 2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
  12. 2023Learning Data Representations with Joint Diffusion Modelscited by 22
29 more
  1. 2021A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networkscited by 19
  2. 2021Invertible DenseNets with Concatenated LipSwishcited by 17
  3. 2022Chroma-VAE: Mitigating Shortcut Learning with Generative Classifierscited by 17
  4. 2021Task-agnostic Continual Learning with Hybrid Probabilistic Modelscited by 16
  5. 2021Autoregressive Quantile Flows for Predictive Uncertainty Estimationcited by 15
  6. 2024A Causal Framework for Evaluating Deferring Systemscited by 13
  7. 2021InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversioncited by 12
  8. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  9. 2022Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flowscited by 9
  10. 2023DejaVu: Conditional Regenerative Learning to Enhance Dense Predictioncited by 9
  11. 2023Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flowcited by 8
  12. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  13. 2023Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learningcited by 7
  14. 2024Taming False Positives in Out-of-Distribution Detection with Human Feedbackcited by 7
  15. 2024Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Modelscited by 5
  16. 2025Synergistic Benefits of Joint Molecule Generation and Property Predictioncited by 5
  17. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  18. 2021Data-driven Cloud Clustering via a Rotationally Invariant Autoencodercited by 2
  19. 2022Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification Systemcited by 2
  20. 2023On the Approximation of Bi-Lipschitz Maps by Invertible Neural Networkscited by 2
  21. 2023De Novo Drug Design with Joint Transformerscited by 2
  22. 2024Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methodscited by 2
  23. 2024FlowCon: Out-of-Distribution Detection using Flow-Based Contrastive Learningcited by 2
  24. 2021Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Modelscited by 0
  25. 2021Deep Generative Models for Vehicle Speed Trajectoriescited by 0
  26. 2023MixerFlow: MLP-Mixer meets Normalising Flowscited by 0
  27. 2025Nash: Neural Adaptive Shrinkage for Structured High-Dimensional Regressioncited by 0
  28. 2025Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Datacited by 0
  29. 2026Sample Efficient Generative Molecular Optimization with Joint Self-Improvementcited by 0