Research map / Learning theory and algorithms / Matrix and tensor methods

Global Optimality for Non-linear Constrained Restoration Problems via Invexity

ICLR 2024 · Learning theory and algorithms › Matrix and tensor methods · approach: Nonconvex low-rank and sparse optimization

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Shows that non-linear constrained signal restoration problems can be posed as invex optimization, giving global optimality guarantees for non-convex formulations.

Problem

Signal restoration via constrained optimization: non-convex formulations reconstruct better than convex ones but lack global optimality guarantees.

Approach

Uses invexity (invex functions, where stationary points are global minima) to obtain global optimality guarantees for non-linear constrained non-convex restoration problems.

Closest papers by meaning

• FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems (CVPR 2025 · similarity 0.86)
• Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · similarity 0.85)
• A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.85)
• Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models (ICML 2025 · similarity 0.84)
• Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems (NeurIPS 2025 · similarity 0.84)
• NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems (NeurIPS 2025 · similarity 0.84)