paper-with-me

Papers

Residual Expansion Algorithm: Fast and Effective Optimization for Nonconvex Least Squares Problems

2017-05-26 · CVPR 2017 7 · Daiki Ikami, Toshihiko Yamasaki, Kiyoharu Aizawa

We propose the residual expansion (RE) algorithm: a global (or near-global) optimization method for nonconvex least squares problems. Unlike most existing nonconvex optimization techniques, the RE algorithm is not based on either stochastic or multi-point searches; therefore, it can achieve fast global optimization. Moreover, the RE algorithm is easy to implement and successful in high-dimensional optimization. The RE algorithm exhibits excellent empirical performance in terms of k-means clustering, point-set registration, optimized product quantization, and blind image deblurring.

📄 PDF Abstract BibTeX arXiv:1705.09549

Code (0)

등록된 구현이 없습니다.

Tasks

Blind Image DeblurringClusteringDeblurringglobal-optimizationImage DeblurringQuantization

Similar Papers 제목 키워드 기반

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks

2024-10-07 · Moonjeong Park, Dongwoo Kim

Oversmoothing has been claimed as a primary bottleneck for multi-layered graph neural networks (GNNs). Multiple analyses have examined how and why oversmoothing occurs. However, none of the prior work addressed how optim…

Deep Sparse Coding Using Optimized Linear Expansion of Thresholds

2017-05-20 · Debabrata Mahapatra, Subhadip Mukherjee, Chandra Sekhar Seelamantula

We address the problem of reconstructing sparse signals from noisy and compressive measurements using a feed-forward deep neural network (DNN) with an architecture motivated by the iterative shrinkage-thresholding algori…

DenoisingImage Denoising

A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks

2026-05-08 · Daning Cheng, Zeyu Liu, Jun Sun, Fen Xia 외 arxiv

The scaling behavior, in which test performance often improves as model size and data increase, is a central empirical phenomenon in modern deep learning, yet its theoretical basis remains incomplete. In this paper, we s…

Online Optimization with Costly and Noisy Measurements using Random Fourier Expansions

2016-03-31 · Laurens Bliek, Hans R. G. W. Verstraete, Michel Verhaegen, Sander Wahls

This paper analyzes DONE, an online optimization algorithm that iteratively minimizes an unknown function based on costly and noisy measurements. The algorithm maintains a surrogate of the unknown function in the form of…

Bayesian Optimization

When Good Enough Is Optimal: Multiplication-Only Matrix Inversion Approximation for Quantized Gated DeltaNet

2026-06-04 · Luoming Zhang, Yuwei Ren, Kui Zhang, Tian Liu 외 arxiv

Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitution-based methods exhibit limited parallelism and poor hardware utili…