mlsanityData to 7 Oct 2026

Benchmarking Invertible Architectures on Inverse Problems

arXiv 2101.10763 ↗First posted 26 Jan 2021cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten invertible architectures and related models fare on two intuitive, low-dimensional benchmark problems, obtaining the best results with coupling layers and simple autoencoders. We hope that our initial efforts inspire other researchers to evaluate their invertible architectures in the same setting and put forth additional benchmarks, so our evaluation may eventually grow into an official community challenge.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 10 of its 14 references that are in the map. First posted on arXiv 26 Jan 2021.

Builds on

10 of 14 references.

References · 10

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  6. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  7. 2018Invertible Residual Networkscited by 364
  8. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  9. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  10. 2018Invertible Autoencoder for domain adaptationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 5; 2023: 4; 2024: 4; 2025: 1; 2026: 4.

25 papers.

Sort:

By area:

  1. 2024Recent Advances on Machine Learning for Computational Fluid Dynamics: A Surveycited by 27
  2. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  3. 2022Autoinverse: Uncertainty Aware Inversion of Neural Networkscited by 16
  4. 2021Inverse design of two-dimensional materials with invertible neural networkscited by 15
  5. 2021Universal Joint Approximation of Manifolds and Densities by Simple Injective Flowscited by 13
  6. 2024Amortized Bayesian Multilevel Modelscited by 12
  7. 2021Inverse deep learning methods and benchmarks for artificial electromagnetic material designcited by 10
  8. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Reviewcited by 8
  9. 2021Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inferencecited by 4
  10. 2022Tackling Multimodal Device Distributions in Inverse Photonic Design using Invertible Neural Networkscited by 3
  11. 2023Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distancescited by 3
  12. 2021Analytically Tractable Hidden-States Inference in Bayesian Neural Networkscited by 2
13 more
  1. 2021RID-Noise: Towards Robust Inverse Design under Noisy Environmentscited by 2
  2. 2022Accelerating Inverse Learning via Intelligent Localization with Exploratory Samplingcited by 2
  3. 2024Learning truly monotone operators with applications to nonlinear inverse problemscited by 2
  4. 2024ISR: Invertible Symbolic Regressioncited by 2
  5. 2022Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modelingcited by 1
  6. 2023Enhancing Inverse Problem Solutions with Accurate Surrogate Simulators and Promising Candidatescited by 1
  7. 2021Fast ABC with joint generative modelling and subset simulationcited by 0
  8. 2022Deep Invertible Approximation of Topologically Rich Maps between Manifoldscited by 0
  9. 2023IDToolkit: A Toolkit for Benchmarking and Developing Inverse Design Algorithms in Nanophotonicscited by 0
  10. 2026Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospectscited by 0
  11. 2026Conservative neural posterior estimation via distributionally robust trainingcited by 0
  12. 2026Generalized Neural Operator for Parametric and Boundary-Value Problemscited by 0
  13. 2026Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulationcited by 0