mlsanityData to 7 Oct 2026

Density Ratio Estimation with Conditional Probability Paths

arXiv 2502.02300 ↗First posted 4 Feb 2025cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Density ratio estimation in high dimensions can be reframed as integrating a certain quantity, the time score, over probability paths which interpolate between the two densities. In practice, the time score has to be estimated based on samples from the two densities. However, existing methods for this problem remain computationally expensive and can yield inaccurate estimates. Inspired by recent advances in generative modeling, we introduce a novel framework for time score estimation, based on a conditioning variable. Choosing the conditioning variable judiciously enables a closed-form objective function. We demonstrate that, compared to previous approaches, our approach results in faster learning of the time score and competitive or better estimation accuracies of the density ratio on challenging tasks. Furthermore, we establish theoretical guarantees on the error of the estimated density ratio.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  12. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
33 more
  1. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  2. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  3. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  4. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 293
  5. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplingscited by 267
  6. 2022Riemannian Score-Based Generative Modellingcited by 216
  7. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  8. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193
  9. 2023Generalization in diffusion models arises from geometry-adaptive harmonic representationscited by 179
  10. 2023The probability flow ODE is provably fastcited by 145
  11. 2019Understanding the Limitations of Variational Mutual Information Estimatorscited by 140
  12. 2020Telescoping Density-Ratio Estimationcited by 108
  13. 2024An analytic theory of creativity in convolutional diffusion modelscited by 103
  14. 2019Flow Contrastive Estimation of Energy-Based Modelscited by 75
  15. 2021Density Ratio Estimation via Infinitesimal Classificationcited by 59
  16. 2023Closed-Form Diffusion Modelscited by 46
  17. 2024Target Score Matchingcited by 46
  18. 2020Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systemscited by 34
  19. 2024Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Samplingcited by 23
  20. 2014High-Dimensional Density Ratio Estimation with Extensions to Approximate Likelihood Computationcited by 19
  21. 2014Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealingcited by 18
  22. 2023Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regressioncited by 17
  23. 2023Gaussian Interpolation Flowscited by 17
  24. 2021Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimationcited by 15
  25. 2023Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyondcited by 13
  26. 2024Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributionscited by 11
  27. 2023Computing high-dimensional optimal transport by flow neural networkscited by 8
  28. 2023Minimizing f-Divergences by Interpolating Velocity Fieldscited by 8
  29. 2024Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifoldscited by 8
  30. 2020Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approachcited by 6
  31. 2022Pitfalls of Gaussians as a noise distribution in NCEcited by 6
  32. 2023Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimationcited by 2
  33. 2024High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matchingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 10.

13 papers.

Sort:

By area:

  1. 2025Learning normalized image densities via dual score matchingcited by 17
  2. 2025Diffusion Secant Alignment for Score-Based Density Ratio Estimationcited by 3
  3. 2026A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimationcited by 3
  4. 2026Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differencescited by 2
  5. 2026Few-Step Boltzmann Generators via Scalable Likelihood Flow Mapscited by 2
  6. 2026One-Step Score-Based Density Ratio Estimationcited by 1
  7. 2026Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winnercited by 1
  8. 2026Multi-Agent Conformal Prediction with Personalized Statistical Validitycited by 1
  9. 2025Learning density ratios in causal inference using Bregman-Riesz regressioncited by 0
  10. 2026Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in Genomicscited by 0
  11. 2026Learning Normalized Energy Models for Linear Inverse Problemscited by 0
  12. 2026Density-aware Sample-specific Attackcited by 0
1 more
  1. 2026Error-Corrected Inference-Time Scaling for Imperfect Diffusion Modelscited by 0