Minimum-Excess-Work Guidance
This work addresses the challenge of data scarcity in scientific applications like molecular simulations by providing a physics-inspired alternative to standard fine-tuning, though it is incremental in applying thermodynamic principles to existing generative models.
The paper tackles the problem of guiding pre-trained generative models in sparse-data regimes by minimizing excess work, a thermodynamic concept, enabling efficient sampling of rare states and alignment with experimental observables. It demonstrates improved sample efficiency and bias reduction on a protein model, achieving better sampling of transition configurations and correction of systematic biases.
We propose a regularization framework inspired by thermodynamic work for guiding pre-trained probability flow generative models (e.g., continuous normalizing flows or diffusion models) by minimizing excess work, a concept rooted in statistical mechanics and with strong conceptual connections to optimal transport. Our approach enables efficient guidance in sparse-data regimes common to scientific applications, where only limited target samples or partial density constraints are available. We introduce two strategies: Path Guidance for sampling rare transition states by concentrating probability mass on user-defined subsets, and Observable Guidance for aligning generated distributions with experimental observables while preserving entropy. We demonstrate the framework's versatility on a coarse-grained protein model, guiding it to sample transition configurations between folded/unfolded states and correct systematic biases using experimental data. The method bridges thermodynamic principles with modern generative architectures, offering a principled, efficient, and physics-inspired alternative to standard fine-tuning in data-scarce domains. Empirical results highlight improved sample efficiency and bias reduction, underscoring its applicability to molecular simulations and beyond.