paper-with-me

Papers

High-arity Sample Compression

2026-05-12 · Leonardo N. Coregliano, William Opich arxiv

Recently, a series of works have started studying variations of concepts from learning theory for product spaces, which can be collected under the name high-arity learning theory. In this work, we consider a high-arity variant of sample compression schemes and we prove that the existence of a high-arity sample compression scheme of non-trivial quality implies high-arity PAC learnability.

📄 PDF Abstract BibTeX arXiv:2605.12465

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Lossy Event Compression based on Image-derived Quad Trees and Poisson Disk Sampling

2020-05-03 · Srutarshi Banerjee, Zihao W. Wang, Henry H. Chopp, Oliver Cossairt 외

With several advantages over conventional RGB cameras, event cameras have provided new opportunities for tackling visual tasks under challenging scenarios with fast motion, high dynamic range, and/or power constraint. Ye…

Event-based visionImage ReconstructionVideo Compression

Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity

2024-12-21 · Dmitry Bylinkin, Aleksandr Beznosikov

In recent years, as data and problem sizes have increased, distributed learning has become an essential tool for training high-performance models. However, the communication bottleneck, especially for high-dimensional da…

Distributed Optimization

AI-Driven Fronthaul Link Compression in Wireless Communication Systems: Review and Method Design

2025-09-05 · Keqin Zhang arxiv

Modern fronthaul links in wireless systems must transport high-dimensional signals under stringent bandwidth and latency constraints, which makes compression indispensable. Traditional strategies such as compressed sensi…

Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?

2024-10-21 · Lingao Xiao, Yang He

In ImageNet-condensation, the storage for auxiliary soft labels exceeds that of the condensed dataset by over 30 times. However, are large-scale soft labels necessary for large-scale dataset distillation? In this paper, …

Dataset DistillationDiversity

The Knowledge Within: Methods for Data-Free Model Compression

2019-12-03 · CVPR 2020 6 · Matan Haroush, Itay Hubara, Elad Hoffer, Daniel Soudry

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision cal…

Model Compression