AI & ML Paradigm Shift

Theoretical analysis proves that Langevin dynamics is fundamentally non-robust to score function errors, justifying the shift to Diffusion Models.

March 13, 2026

Original Paper

On the Robustness of Langevin Dynamics to Score Function Error

Daniel Yiming Cao, August Y. Chen, Karthik Sridharan, Yuchen Wu

arXiv · 2603.11319

The Takeaway

While practitioners have largely moved to diffusion, this paper provides the mathematical proof that Langevin dynamics fail in high dimensions even with small score errors. This provides a rigorous foundation for why diffusion's time-dependent score estimation is necessary.

From the abstract

We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the L^2 errors (more generally L^p errors) in the estimate of the score function. It is well-established that with small L^2 errors in the estimate of the score function, diffusion models can sample faithfully from the target distribution under fairly mild regularity assumptions in a polynomial time horizon. In contrast, our