paper-with-me

Papers

IHT dies hard: Provable accelerated Iterative Hard Thresholding

2017-12-26 · Rajiv Khanna, Anastasios Kyrillidis

We study --both in theory and practice-- the use of momentum motions in classic iterative hard thresholding (IHT) methods. By simply modifying plain IHT, we investigate its convergence behavior on convex optimization criteria with non-convex constraints, under standard assumptions. In diverse scenaria, we observe that acceleration in IHT leads to significant improvements, compared to state of the art projected gradient descent and Frank-Wolfe variants. As a byproduct of our inspection, we study the impact of selecting the momentum parameter: similar to convex settings, two modes of behavior are observed --"rippling" and linear-- depending on the level of momentum.

📄 PDF Abstract BibTeX arXiv:1712.09379

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ItNet: iterative neural networks with small graphs for accurate, efficient and anytime semantic segmentation

2021-01-21 · Thomas Pfeil

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low …

Semantic Segmentation

Hardware Architecture Design of Model-Based Image Reconstruction Towards Palm-size Photoacoustic Tomography

2024-08-12 · Yuwei Zheng, Zijian Gao, Yuting Shen, Jiadong Zhang 외

Photoacoustic (PA) imaging technology combines the advantages of optical imaging and ultrasound imaging, showing great potential in biomedical applications. Many preclinical studies and clinical applications urgently req…

CPUImage Reconstruction

CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning

2026-05-07 · Sonu Kumar, Mukul Lokhande, Santosh Kumar Vishvakarma, Adam Teman arxiv

This paper presents CARMEN, a runtime-adaptive, CORDIC-accelerated multi-precision vector engine for resource-efficient deep learning inference. The key insight is that CORDIC iteration depth directly governs computation…

Real-Time Object Detection

Provable Inductive Robust PCA via Iterative Hard Thresholding

2017-04-02 · U. N. Niranjan, Arun Rajkumar, Theja Tulabandhula

The robust PCA problem, wherein, given an input data matrix that is the superposition of a low-rank matrix and a sparse matrix, we aim to separate out the low-rank and sparse components, is a well-studied problem in mach…

Accelerated Neural Networks on OpenCL Devices Using SYCL-DNN

2019-04-08 · Rod Burns, John Lawson, Duncan McBain, Daniel Soutar

Over the past few years machine learning has seen a renewed explosion of interest, following a number of studies showing the effectiveness of neural networks in a range of tasks which had previously been considered incre…

CPUGPU