cs.LGApr 16, 2026

Learning Affine-Equivariant Proximal Operators

Authors: Oriel Savir, Zhenghan Fang, Jeremias Sulam

Organizations: Mathematical Institute for Data Science, Johns Hopkins University, Baltimore, MD 21218, USA

Abstract

Proximal operators are fundamental across many applications in signal processing and machine learning, including solving ill-posed inverse problems. Recent work has introduced Learned Proximal Networks (LPNs), providing parametric functions that compute exact proximals for data-driven and potentially non-convex regularizers. However, in many settings it is important to include additional structure to these regularizers--and their corresponding proximals--such as shift and scale equivariance. In this work, we show how to obtain learned functions parametrized by neural networks that provably compute exact proximal operators while being equivariant to shifts and scaling, which we dub Affine-Equivariant Learned Proximal Networks (AE-LPNs). We demonstrate our results on synthetic, constructive examples, and then on real data via denoising in out-of-distribution settings. Our equivariant learned proximals enhance robustness to noise distributions and affine shifts far beyond training distributions, improving the practical utility of learned proximal operators

Explore similar work

Date pendingmath.NA

Deep learning methods for inverse problems using connections between proximal operators and Hamilton-Jacobi equations

Inverse problems are important mathematical problems that seek to recover model parameters from noisy data. Since inverse problems are often ill-posed, they require regularization or incorporation of prior information about the underlying model or unknown variables. Proximal operators, ubiquitous in nonsmooth optimization, are central to this because they encode priors and yield efficient iterative algorithms. They have also recently become key to modern machine learning methods, e.g., plug-and-play methods with learned denoisers and deep neural architectures for learning priors of proximal operators. The latter was developed partly due to recent work characterizing proximal operators of nonconvex priors as subdifferentials of convex potentials. In this work, we propose to leverage connections between proximal operators and Hamilton--Jacobi partial differential equations (HJ PDEs) to develop deep learning architectures for learning the prior. In contrast to other existing methods, we learn the prior directly without recourse to inverting the prior after training. We present numerical results in dimensions up to 6464, where the recovered prior is evaluated in a single forward pass.
Oluwatosin Akande, Gabriel P. Langlois, Akwum Onwunta
May 5, 2026cs.CV

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

Normalization Equivariance (NE) is a structural prior that improves robustness to distribution shift in image-to-image tasks. A function ff is normalization equivariant iff f(ay+b1)=af(y)+b1f(a y + b\mathbf{1}) = a f(y) + b\mathbf{1} for all a>0a>0 and b∈Rb\in\mathbb{R}. Existing NE methods constrain every internal layer to NE-compatible operations. These constraints add runtime cost and exclude standard transformer components such as softmax attention and LayerNorm. We introduce Wrapped Normalization Equivariance (WNE), a parameter-free wrapper that normalizes the input, applies any backbone, and denormalizes the output. We prove every NE function admits this factorization, so the wrapper exactly parameterizes the class of NE functions. On blind denoising, wrapping CNN and transformer architectures improves robustness under noise-level mismatch with no measurable GPU overhead, while architectural NE baselines are up to 1.6×1.6\times slower.
Youssef Saied, François Fleuret
Jul 16, 2026eess.IV

Domain Adaptation of Mismatched Proximal Denoiser for Plug-and-Play Image Reconstruction

Plug-and-play proximal gradient descent (PnP-PGD) enables flexible image reconstruction by using denoisers as implicit priors. In practice, these denoisers are often deployed outside their training domains. Existing analyses establish convergence under structural assumptions on the deployed denoiser, such as requiring it to be a proximal map or a contraction. However, they do not measure how domain mismatch affects convergence of PnP-PGD. We define this effect as \emph{proximal mismatch}: the discrepancy between a deployed denoiser D^\widehat{\mathsf D} and a target-domain reference map D⋆=prox⁡R⋆\mathsf D_\star=\operatorname{prox}_{R_\star} associated with the underlying regularizer R⋆R_\star. Under this mismatch, each denoising update becomes an inexact proximal step for the target objective. We further derive a stationarity bound that decays at a rate of O(1/K)\mathcal{O}(1/K), with an additive term proportional to the average squared proximal mismatch. This result motivates adaptation via proximal matching rather than MSE-based adaptation alone. We study this approach with two established denoiser families: learned proximal networks and gradient-step denoisers. Experiments on Gaussian deblurring and super-resolution under substantial domain shift show that proximal matching adaptation improves reconstruction quality significantly over MSE-based adaptation, yielding the largest numerical gains in the few-shot regime.
Guixian Xu, Jinglai Li, Junqi Tang