Recovery-Directed Symbolic Distillation of Neural Likelihoods

arXiv:2609.32409 · cs.LG, q-bio.NC, stat.CO, stat.ML · Submitted 2026-09-26 · Read on arXiv

cs.LG, q-bio.NC, stat.CO, stat.ML

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Calibration — 12× in this paper · explained in 7 episodes
• Distillation — 11× in this paper · explained in 2 episodes
• Simulation-based Inference — 6× in this paper · explained in 2 episodes
• Symbolic Regression — 6× in this paper · explained in 5 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Generative AI — 4× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Normalizing Flow — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Simulation-Based Inference (SBI) — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
• Bayesian Workflow
• Symbolic Density Estimation for Discrete Distributions
• Symbolic Density Estimation: A Decompositional Approach
• Validating Bayesian Inference Algorithms with Simulation-Based Calibration
• SymTorch: Symbolic Distillation of Neural Networks

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks