Livin' on a Prior: Likelihood Score Approximation for Inverse Problems

arXiv:2609.34446 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/zhangbingliang2019/DAPS4https:

Terminology

• Inverse Problem — 1× in this paper · explained in 2 episodes

Sources

• Conditional Image Generation with Score-Based Diffusion Models
• Conditional flow matching for physics-constrained inverse problems with finite training data
• AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks