AI & ML
Inverse Design for Conditional Distribution Matching
arXiv stat.ML0 views
arXiv:2605.09439v2 Announce Type: replace-cross Abstract: Generative models are powerful tools for sampling from a learned distribution $\mathcal{P}(Y \mid X)$, and inverse-design methods invert this map to find an input $x$ that produces a desired point output $y^*$. However, many design goals are naturally distributional rather than pointwise, incorporating the inherent uncertainty of $Y$ and targeting a specific form for it, a task not addressed by standard inverse design. To address this issue we introduce Conditional Distribution Matching (CDM), a new inverse-design problem class in generative modeling: given a joint distribution $\mathcal{P}(X, Y)$ and a target distribution $\mathcal{G}(Y)$, find an input $x^*$ whose induced conditional distribution $\mathcal{P}(Y \mid X = x^*)$ matches $\mathcal{G}$. We formally define two variants: Conditional Distribution Matching Sampling (CDMS) and Conditional Distribution Matching Optimization (CDMO). To solve these problems, we propose MLGD-F (Matching-Loss Guided Diffusion with a Fast inner sampler), a plug-and-play inference-time algorithm that combines a pretrained score-based diffusion model with a pretrained fast conditional sampler, requiring no additional training or fine-tuning. By leveraging single-step conditional sampling, MLGD-F enables tractable gradient computation, making the estimation of $\mathcal{P}(Y \mid X)$ both memory-efficient and computationally lightweight. We validate MLGD-F on synthetic benchmarks, structured image transformations, and generative editing optimization, demonstrating reliable recovery of inputs whose conditional distributions match diverse user-specified targets, including discrete mixtures and continuous low-rank supports.
Source:https://arxiv.org/abs/2605.09439PreviousOptimistic Actor-Critic with Parametric Policies for Linear Markov Decision ProcessesNextBad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
Related posts
Eval-Driven Development: How to Test AI Features Beyond Traditional Unit Tests
0dev.to Testing

A RAG answer can cite every sentence and still be wrong: a script to reproduce it
0dev.to Testing
![Vision Language Action Models — Ch.09: Generalist Robot Policies [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fiu9r3c6ct01wklmuk30s.png)
Vision Language Action Models — Ch.09: Generalist Robot Policies [EN]
0dev.to Programming
![Vision Language Action Models — Ch.08: Humanoid VLA Architectures [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fwvvm5efdgcglkt54bd4u.png)
Vision Language Action Models — Ch.08: Humanoid VLA Architectures [EN]
0dev.to Programming
![Vision Language Action Models — Ch.06: Language to Action Pipelines [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fwnqy6w0otpzb0uvivwn8.png)
Vision Language Action Models — Ch.06: Language to Action Pipelines [EN]
0dev.to Programming
![Vision Language Action Models — Ch.05: Vision Language Models [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fbw5a20v9raz6duiimhzg.png)
Vision Language Action Models — Ch.05: Vision Language Models [EN]
0dev.to Programming