---
title: Unadjusted Langevin Algorithm (ULA)
url: https://www.emergentmind.com/topics/unadjusted-langevin-algorithm-ula
type: topic
---

# Unadjusted Langevin Algorithm (ULA)

The Unadjusted Langevin Algorithm (ULA) is a widely used discretization of overdamped Langevin dynamics for sampling from complex, high-dimensional probability distributions with densities known up to a normalization constant. ULA has become central in scalable Bayesian inference, machine learning, and computational statistics, with a rigorous research literature spanning smooth and non-smooth analysis, convergence rates, high-dimensional scaling, algorithmic enhancements, and extensions to non-convex and non-log-concave regimes.

## 1. Mathematical Formulation and Core Mechanism

ULA is derived by discretizing the continuous-time Langevin SDE targeting a density $\pi(x) \propto \exp(-U(x))$ on $\mathbb{R}^d$ with a potential $U:\mathbb{R}^d\to\mathbb{R}$:
\[
dX_t = -\nabla U(X_t)\,dt + \sqrt{2}\,dB_t,
\]
where $B_t$ is standard $d$-dimensional Brownian motion. The ULA iteration, using a constant or variable step size $h > 0$, updates as:
\[
X_{k+1} = X_k - h\,\nabla U(X_k) + \sqrt{2h}\;\xi_{k+1},\quad \xi_{k+1} \sim N(0, I_d).
\]
The algorithm forms a non-reversible Markov chain whose stationary law $\pi_h$ approximates the target $\pi$ as $h\to 0$. Empirical averages converge to expectations under $\pi$ with a step size–dependent bias [1507.05021].

## 2. Theoretical Convergence Analysis

### Strongly Log-Concave and Smooth Potentials

When $U$ is strongly convex ($\nabla^2 U \succeq m I$) and $\nabla U$ is $L$-Lipschitz, non-asymptotic convergence in $W_2$ and total variation distances is exponential; the bias term $W_2(\pi_h,\pi) = O(\sqrt{d}\,h)$, and the mixing rate is geometric in $k$ with rate $1 - O(mh)$, provided $h < 1/(m + L)$ [1605.01559, 1802.09188, 1507.05021]. The bias–variance trade-off necessitates $h = O(\varepsilon^2/d)$ for $W_2$ error $\le \varepsilon$ [2408.13115].

### Weakly Smooth, Non-Convex, and Superlinear Potentials

For non-convex or merely weakly-smooth (e.g., Hölder or “mixture $a$-weakly smooth”) potentials, ULA convergence can still be established by smoothing the potential or using convexification strategies. For mixture $a$-weak smoothness, balancing smoothing and discretization leads to polynomial iteration complexity in $d$ and $1/\varepsilon$ [2101.06369]. Without global Lipschitzness but with appropriate dissipativity and functional inequalities (e.g., LSI, Poincaré, Talagrand), ULA achieves $W_2$ and KL convergence with step size $h = O(\varepsilon^{1/(1 + a)})$ [2101.06369]. 

Superlinear drifts may cause classical ULA to diverge. The Tamed ULA (TULA) replaces the drift $\nabla U(x)$ by a bounded approximation, ensuring stability and preserving $O(\sqrt{h})$ bias and geometric convergence under weak conditions [1710.05559].

### Non-Smooth and Discontinuous Gradients

For targets with non-smooth or pointwise discontinuous gradients, ULA and its subgradient variant (SG-ULA) converge with reduced rates. If the drift is piecewise Lipschitz or obeys only linear growth, the stepsize bias degrades to $O(h^{1/2})$ or $O(h^{1/4})$ in $W_p$, but convergence in Wasserstein distance still holds under suitable dissipativity and moment bounds [2312.01950, 2502.03458]. For convex but non-differentiable $U$, stochastic subgradient or proximal extensions of ULA (SSGLD, SPGLD) provide convergence guarantees by leveraging convex optimization tools [1802.09188, 1802.08671].

## 3. Algorithmic Enhancements and Extensions

### Transport Map and Geometry-Informed ULA

Transport map–based ULA (TMULA) leverages an invertible map $T$ that pushes $\pi$ towards a tractable reference measure. Discretizing Langevin dynamics in the mapped space yields preconditioned or Riemannian manifold dynamics, and learning $T$ (e.g., by normalizing flows) systematically accelerates sampling, enhancing strong convexity and conditioning [2302.07227, 2304.08342]. Geometry-informed irreversible perturbations further accelerate mixing by introducing skew-symmetric drift [2302.07227].

### Proximal and Double-Loop ULA

Proximal ULA schemes split the update into a proximal step for non-smooth terms and a Gaussian perturbation, aligning with the JKO-splitting of Wasserstein gradient flows. This broadens applicability to composite and non-smooth posteriors [1802.08671]. Double-loop step-size schedules (DL-ULA) improve convergence under light-tail (non-strong-convex) conditions by alternating fast-mixing batches and step-size reductions, providing first non-asymptotic $W_2$ guarantees in high dimension for log-concave targets [2007.01147].

### Preconditioning and Domain-Specific Schemes

Preconditioned ULA applies a matrix-valued adaptation to both drift and noise, flattening quadratic curvature and reducing the effective condition number. In inverse problems, notably MRI reconstruction, this permits larger steps, faster mixing, and robust uncertainty quantification with minimal parameter tuning [2512.05791]. Hybrid approaches incorporating data-driven priors or denoisers (e.g., with plug-and-play or learned normalizing flows) integrate deep models for the prior, with theoretical well-posedness and practical acceleration [2304.08342].

## 4. Convergence Metrics, High-Dimensional Scaling, and Bias Localization

Convergence guarantees for ULA are typically given in total variation, $W_2$, KL, or Rényi divergences. Recent work distinguishes between global and marginal (partial coordinate) convergence: while $W_2(\pi_h, \pi) \propto \sqrt{d h}$, marginal bias for $K$-dimensional coordinates is $O(\sqrt{K h \log d})$. This effect, called "delocalization of bias," means that low-dimensional projections can mix on $O(K \log d/\varepsilon^2)$ timescales, even when full-dimensional convergence is slower; this is particularly sharp for Gaussian targets and strongly log-concave measures with sparse graphical structure [2408.13115].

| Metric        | Classical ULA   | DL-ULA        | TULA    | Weak-smooth/Non-smooth | High-dim delocalization   |
|---------------|----------------|--------------|---------|------------------------|---------------------------|
| $W_2$         | $O(\sqrt{d h})$| $O(d^9 T^{-1/6})$ | $O(\sqrt{h})$ | $O(h^{1/(1+a)})$–$O(h^{1/2})$ | $O(\sqrt{K h \log d})$ for $K$-marginals   |
| TV            | $O(d h)$       | $O(d^3 T^{-1})$   | $O(\sqrt{h})$ | $O(h^{1/2})$              |                           |
| KL            | $O(d h)$       | $O(d^3 T^{-2/3})$ | $O(h)$         | $O(h^{1+a})$              |                           |

## 5. Functional Inequalities, Mixing, and Isoperimetry

ULA’s convergence in KL and Rényi divergences is controlled by functional inequalities satisfied by the target and its discretization bias. Log-Sobolev inequalities (LSI) suffice for exponential decay of relative entropy without requiring convexity, provided the Hessian is bounded; the key recursion is:
\[
H_\nu(\rho_{k+1}) \leq e^{-\alpha \eta} H_\nu(\rho_k) + O(\eta^2 n L^2)
\]
where $H_\nu$ is KL and $n$ the dimension [1903.08568]. Under LSI or Poincaré for the target, with $L$-smoothness, ULA achieves explicit geometric convergence in KL or Rényi divergence, with iterates reaching $\epsilon$-precision in $O(L^2 n/\alpha^2)$ steps for an optimal step size [1903.08568]. Bias vanishes as stepsize $\eta\to 0$ given third-order smoothness.

Empirically, ULA’s exponential decay of $\Phi$-mutual information corresponds to effective mixing and rapid "decorrelation" of samples, with strong convexity and LSI controlling independence time and necessary burn-in [2402.17067].

## 6. Practical Aspects and Implementation Guidance

Step size must be chosen according to drift smoothness, strong convexity, and, in the non-smooth or non-convex case, according to local polynomial-Lipschitz bounds and dissipativity. For stability and accuracy:
- $h < 1/(m + L)$ for strongly convex and Lipschitz $\nabla U$.
- $h = O(\varepsilon^2/d)$ for $W_2$ error $\le \varepsilon$.
- For TULA and non-smooth cases, $h$ must be further reduced and sometimes coordinatewise taming used [1710.05559].
- For weak smoothness (mixture $a$), $h = O(\varepsilon^{1/(1 + a)})$ [2101.06369].
- For high-dimensional applications, delocalization implies $h = O(\varepsilon^2/(K \log d))$ for $K$-marginal error $\le \varepsilon$ [2408.13115].

Extensions to multiplicative noise, proximal steps, stochastic (minibatch) gradients, and non-Euclidean/geometry-informed corrections expand the practical utility of ULA in modern Bayesian computation [2012.14310, 1802.09188, 2302.07227].

## 7. Limitations, Open Problems, and Future Directions

Despite broad theoretical guarantees, limitations of ULA include discretization bias (which may persist outside the strongly convex regime), possible instability for aggressive step sizes or superlinear drifts, and slow mixing for severely ill-conditioned or multimodal targets. Ongoing research addresses:
- Reducing asymptotic bias via adaptive step-size, MALA-corrections, or transport-based preconditioning [2302.07227, 2512.05791].
- Robustness to non-smoothness and low regularity, with convergence rates for SG-ULA/SPGLD in high dimensions [2502.03458].
- Extension of delocalization results to broader classes of non-Gaussian and non-sparse targets [2408.13115].
- Integration of structural priors, normalizing flows, or data-driven denoising modules in large-scale inverse problems and imaging [2304.08342].
- Quantitative guidance for parameter selection balancing efficiency versus accuracy in realistic workloads.

ULA remains an active subject of research as both a foundation for high-dimensional sampling algorithms and a testbed for theoretical developments in stochastic processes, optimization in measure spaces, and computational statistics.

Source: https://www.emergentmind.com/topics/unadjusted-langevin-algorithm-ula