- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
Let be a probability density function of the form where is the normalizing constant and is a potential function defined on . The goal of the paper is to analyze the METROPOLIS-ADJUSTED SUBDIFFERENTIAL LANGEVIN SAMPLING (MASLA) algorithm, which samples a random variable having a distribution close to the target . It is assumed that one has access to a measurable version of the conservative field of . Main results show that the MASLA algorithm is well-defined and geometrically ergodic under some conditions. I find these results interesting, but of limited importance compared to the standards of the top ML conferences. The paper also provides some numerical experiments, which are interesting. However, these experiments do not allow us to conclude that MASLA is better than the proximal algorithm.
Critical strengths
The problem of sampling from an unknown density has been central in theoretical and applied ML. The paper is easy to read; the main related work seems to be appropriately cited.
Critical weaknesses
The main contributions appear to be rather incremental. Having geometric ergodicity without any evaluation of and is an important limitation. Another weakness is the lack of an example of that has some practical importance and for which the other existing approaches do not work as well as the present one. In other words, the current paper appears as a conceptual extension of existing methods and theories, rather than a study motivated by some concrete needs.
Minor remarks
- Page 2, just after eq 2.1: it should be mentioned that is independent of the Brownian motion .
- Section 2: for a fair account, it should be mentioned here that if the dimension is large (say, larger than 20) the acceptance rate of MALA can drop to a value very close to zero. This results in a very high computational cost of MALA in large dimensions.
- Eq (3.5): notation is not defined at this stage
- Example 3.2: the Clarke subdifferential is mentioned here, without any connection to the notion of a conservative field.
- My feeling is that there is not enough novelty in Proposition 3.3 to state it as a proposition. This result directly follows from well-known facts.
Questions for authors
I have no question.
4 comments
Official comment to Reviewer z6CX
- Two new high-dimensional real data analyses
We have added two inverse problems using measured data to complement the synthetic benchmarks. Both use nonsmooth nonconvex posterior models and compare MASLA and USLA at matched steps and update budgets. Each setting uses four independent repetitions of four chains, with updates and burn-in updates per chain.
Walnut X-ray tomography: Section 5.4, p. 9; Figure 4, p. 10; Appendix G, pp. 69–72; Table 3, p. 71. We reconstruct an image, giving unknowns, from measured walnut X-ray projections. The posterior combines a Gaussian observation model and ridge prior with capped total variation. This penalty makes the posterior nonsmooth and nonconvex while preserving the quadratic-plus-Lipschitz structure of our theoretical class. Sixty measured angles define the target, and thirty held-out angles assess prediction. MASLA increases mean held-out pointwise log predictive density from to and reduces prediction root mean squared error (RMSE) from to . All four repetitions favor MASLA on both reported predictive metrics, and the exploratory paired intervals exclude zero. These results assess prediction of unseen physical measurements, not merely numerical stability.
Optical phase retrieval: Section 5.5 and Table 1, p. 10; Appendix H, pp. 73–76; Figure 10, p. 76. We use measured optical transmission-matrix data for three real input patterns, each with unknowns. The Gaussian amplitude likelihood leads to a nonsmooth nonconvex posterior with a quadratic-plus-Lipschitz decomposition. Each image is evaluated at two shared step sizes. We assess the absolute radial Stein residual using the exact posterior identity Its known target value avoids reliance on an approximate reference chain. MASLA reduces the mean absolute residual by – at the larger steps and – at the smaller steps. All image–step–repetition pairs favor MASLA, and all six exploratory paired intervals exclude zero. This checks agreement with an exact posterior moment in addition to stability.
These applications provide high-dimensional evidence at and , alongside the expanded study. The reported predictive and moment diagnostics are selected finite-run comparisons. The appendices provide the models, data preparation, simulation settings, and uncertainty calculations.
- Practical motivation and the scope of comparisons
We agree that the submitted experiments did not establish superiority over proximal algorithms. The revised paper does not make a general claim of that kind. The convex benchmark in Section 5.1, p. 8, remains a comparison with established samplers; the new applications address the additional question of practical relevance for nonsmooth nonconvex targets that those algorithms are not directly applicable.
For each real-data example, we have added a specific discussion of why the cited competing frameworks do not directly apply: Section G.1, p. 70, for walnut tomography, and Section H.1, p. 74, for optical phase retrieval. The nonconvex potentials violate the convex-composite assumptions of Grad-sub and Prox-sub and the log-concavity and convex proximal/Moreau assumptions of the cited P-MALA and MYULA frameworks. In phase retrieval, we further show that the full-potential proximal map at zero is not single-valued. Classical gradient-based ULA/MALA also require an additional selection convention at the nonsmooth states. These discussions identify the specific assumptions and constructions that fail for our models.
We have also added an explanation of why MASLA can improve on USLA. In Section H.2, p. 75, equation (H.8) derives a positive-step discrepancy in the radial Stein identity for USLA: if its stationary law exists with the required finite moments, its normalized radial moment exceeds the target value by . MASLA's MH correction preserves the intended target, for which this discrepancy is zero. This provides a mathematical mechanism for the smaller Stein residuals observed in the phase-retrieval experiments.
Official comment to Reviewer z6CX
- Changes addressing the minor remarks
(i) Independence of the initial condition and Brownian motion. We now explicitly state immediately after equation (2.1), Section 2, p. 3, that the initial state is independent of the driving Brownian motion.
(ii) Acceptance and computational cost in high dimension. Section 2, pp. 3–4, now explains that acceptance can approach zero when the step size is too large relative to dimension and target geometry, and that reducing the step size can also reduce movement per iteration. It discusses the classical dimension-dependent MALA scaling under its stated smooth-target assumptions.
(iii) Undefined differentiability-set notation. Section 3, p. 4, now defines and distinguishes this set from the conservative field . We further added a notation table in Appendix I on pp. 77–79.
(iv) Connection between the Clarke subdifferential and conservative fields. Example 3.2, p. 4, now refers explicitly to Definition B.8 and Propositions B.9–B.10, p. 23. Proposition B.10 relates the chain rule for the Clarke subdifferential to its conservative-field property, and Section B.2 verifies that chain rule for the example. Proposition B.9(ii) also explains that, whenever a locally Lipschitz function admits a conservative field, its Clarke subdifferential is conservative. The example therefore connects its subdifferential calculation to the field used in the algorithm.
(v) Status and placement of the former Proposition 3.3. We agree that exact invariance follows from standard MH arguments and should not be presented as a novel contribution. The full statement has been moved to Appendix, Proposition B.14 in Section B.2, p. 25. Section 3 retains a brief sentence referring readers to that result.
Follow-up before the discussion concludes
Dear Reviewer z6CX,
Thank you again for your careful review and constructive suggestions. As the discussion period draws to a close, we would like to briefly summarize how we addressed your main concerns:
- Explicit geometric convergence constants: We added Theorem 4.5, which makes the geometric convergence constants and explicitly computable and provides a corresponding iteration bound, rather than leaving the rate purely qualitative.
- Practical motivation and real-data applications: We added two real-data nonsmooth nonconvex inverse problems—walnut X-ray tomography with and optical phase retrieval with —for which the cited convex proximal and smooth-gradient frameworks are not directly applicable.
- Why MASLA can improve on the unadjusted method: We added a mathematical explanation showing a positive-step discrepancy in the radial Stein identity for USLA, while the MH correction in MASLA preserves the intended target and removes this discrepancy.
- Minor comments: We addressed all five points concerning independence assumptions, high-dimensional MALA acceptance, notation, the connection between Clarke subdifferentials and conservative fields, and the presentation of the standard MH invariance result.
If these revisions resolve your concerns, we would greatly appreciate it if you could consider reflecting this in your assessment.
Best regards,
Authors
Official comment to Reviewer z6CX
Thank you for your careful review. We agree that geometric ergodicity without evaluating its constants was an important limitation of the submitted manuscript. To address this concern, we have added Theorem 4.5 in Section 4.4, p. 7, which gives computable geometric convergence constants for MASLA under the assumptions of the geometric-ergodicity theorem. Its rigorous proof is provided in Section D.2, pp. 51–54, using the quantitative coupling result in Section D.1, pp. 48–50. We also agree that practical applications were needed to establish the relevance of the method. We have added two high-dimensional real-data analyses that existing methods are not directly applicable.
The revised manuscript contains 79 pages in total, with the notation table in Appendix I on pp. 77–79, while keeping the main text within 10 pages. The computable geometric constants, two high-dimensional real-data analyses, expanded numerical accuracy study, and clarifications above substantially strengthen both the theoretical content and practical motivation. Below, all page references refer to the revised file.
The submitted result established geometric ergodicity but did not evaluate Mγ and ργ. Theorem 4.5 now constructs both constants for the class U(x)=21x⊤Hx+g(x), where H is symmetric positive definite and g is globally L-Lipschitz with a conservative field bounded by B. The selected drift is β(x)=Hx+v(x) with ∥v(x)∥≤B. Writing h− and h+ for the extreme eigenvalues of H, the result holds at every fixed step size 0<γ<2/h+. It allows nonconvex g and does not require a warm start.
Specifically, the proof evaluates drift constants 0<θ<1 and b>0 and a minorization constant 0<ϵγ≤1/2 from d,h−,h+,L,B, and γ. With V(x)=1+∥x∥2, these satisfy
\qquad R_\gamma(x,\cdot)\geq\epsilon_\gamma\nu_{C_S}(\cdot)\quad(x\in C_S),$$ where $S=\max\{4,4b/(1-\theta)\}$, $C_S=\{x:V(x)\leq S\}$, and $\nu_{C_S}$ is normalized Lebesgue measure on $C_S$. Equation (4.8), p. 7, specifies $$\eta_\gamma=\frac{\epsilon_\gamma}{2b},\qquad M_\gamma=1+\frac{2}{\eta_\gamma}+\frac{b}{1-\theta} \qquad\text{and}\qquad \rho_\gamma=1-\frac{\epsilon_\gamma}{2+\eta_\gamma S}.$$ Theorem 4.5 proves that these choices satisfy $M_\gamma<\infty$, $0<\rho_\gamma<1$, and the bound in equation (4.9). The estimate concerns the MASLA kernel itself and includes initialization at nondifferentiable points. The proof evaluates the quantities entering these formulas, rather than leaving them as unspecified drift or minorization constants. First, it bounds the exact log MH ratio and constructs an acceptance radius in equations (D.7)–(D.9), pp. 51–52. Second, it derives the drift radius and inequality in equations (D.10)–(D.11), p. 52. Third, it constructs a common minorization on the required enlarged set in equations (D.12)–(D.13), p. 53. Finally, the weighted coupling bound of Lemma D.1 converts these estimates into the displayed $M_\gamma$ and $\rho_\gamma$. The construction uses the stated model bounds and does not require evaluating the target normalizing constant. Corollary D.2, p. 54, also gives a sufficient iteration count for an initial distribution $\mu$ with $\mu(V)<\infty$. For requested accuracy $0<\varepsilon<1$, it suffices to take $$n\geq\left\lceil\frac{\log(M_\gamma\mu(V)/\varepsilon)}{-\log\rho_\gamma}\right\rceil$$ to obtain $\|\mu R_\gamma^n-\pi\|_V\leq\varepsilon$. Thus the revision provides an evaluable rate and prefactor, as well as an iteration bound. These constants work for all requested accuracies at the fixed step size.