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

Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates

NeurIPS 2026 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization

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.

Studies how noisy perturbations combined with over-parametrization improve the optimization landscape of matrix completion, via epsilon-close surrogate problems.

Problem

Non-convex matrix completion lacks a principled optimization framework; the paper aims to understand how noisy perturbations and over-parametrization together shape the landscape of recovery from partially observed matrices.

Approach

Uses epsilon-close surrogate objectives, combining noisy perturbations with over-parametrization, to improve the optimization landscape of matrix completion, as stated in the abstract.

Closest papers by meaning

• Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.90)
• Generalization Bounds for Inductive Matrix Completion in Low-Noise Settings (AAAI 2023 · similarity 0.90)
• Fast exact recovery of noisy matrix from few entries: the infinity norm approach (NeurIPS 2025 · similarity 0.89)
• Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.88)
• Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.88)
• How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization (ICLR 2024 · similarity 0.88)