REVIEW 4 cited by
Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Variational regularisation is the primary method for solving inverse problems, and recently there has been considerable work leveraging deeply learned regularisation for enhanced performance. However, few results exist addressing the convergence of such regularisation, particularly within the context of critical points as opposed to global minimisers. In this paper, we present a generalised formulation of convergent regularisation in terms of critical points, and show that this is achieved by a class of weakly convex regularisers. We prove convergence of the primal-dual hybrid gradient method for the associated variational problem, and, given a Kurdyka-Lojasiewicz condition, an $\mathcal{O}(\log{k}/k)$ ergodic convergence rate. Finally, applying this theory to learned regularisation, we prove universal approximation for input weakly convex neural networks (IWCNN), and show empirically that IWCNNs can lead to improved performance of learned adversarial regularisers for computed tomography (CT) reconstruction.
Forward citations
Cited by 4 Pith papers
-
Distributed Stochastic Optimization for Non-Smooth and Weakly Convex Problems under Heavy-Tailed Noise
A clipping-based distributed subgradient method is proven to converge for non-smooth weakly convex problems under heavy-tailed noise, with an O(1/log T) stationarity rate.
-
MAP Image Recovery with Guarantees using Locally Convex Multi-Scale Energy (LC-MUSE) Model
A locally convex multi-scale energy prior with local monotonicity constraints gives provable reconstruction guarantees and MRI results that match non-convex deep baselines.
-
Benchmarking learned algorithms for computed tomography image reconstruction tasks
A reproducible benchmark of learned CT reconstruction methods on real experimental data, covering post-processing, unrolled, learned regularizer, and plug-and-play methods across five tasks.
-
Weakly-Convex Regularization for Magnetic Resonance Image Denoising
A weakly-convex Welsch-activated denoiser matches Patch2Self on diffusion MRI while producing fewer tractography artifacts.
Discussion (0). Continue with ORCID to comment.