paper-with-me

Papers

Dynamic Universal Approximation Theory: Foundations for Parallelism in Neural Networks

2024-07-31 · Wei Wang, Qing Li

Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks. However, this approach introduces an urgent problem: current deep learning models are predominantly serial, meaning that as the number of network layers increases, so do the training and inference times. This is unacceptable if deep learning is to continue advancing. Therefore, this paper proposes a deep learning parallelization strategy based on the Universal Approximation Theorem (UAT). From this foundation, we designed a parallel network called Para-Former to test our theory. Unlike traditional serial models, the inference time of Para-Former does not increase with the number of layers, significantly accelerating the inference speed of multi-layer networks. Experimental results validate the effectiveness of this network.

📄 PDF Abstract BibTeX arXiv:2407.21670

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Dynamic Universal Approximation Theory: The Basic Theory for Transformer-based Large Language Models

2024-07-01 · Wei Wang, Qing Li

Language models have emerged as a critical area of focus in artificial intelligence, particularly with the introduction of groundbreaking innovations like ChatGPT. Large-scale Transformer networks have quickly become the…

In-Context Learning

Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation

2026-06-25 · Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim, Gregory Cousins 외 arxiv

Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily captures complexity through regularity, and the…

DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks

2020-11-01 · Shiyun Xu, Zhiqi Bu

Recent years have witnessed strong empirical performance of over-parameterized neural networks on various tasks and many advances in the theory, e.g. the universal approximation and provable convergence to global minimum…

feature selectionvalid

Elementos da teoria de aprendizagem de máquina supervisionada

2019-10-06 · Vladimir G. Pestov

This is a set of lecture notes for an introductory course (advanced undergaduates or the 1st graduate course) on foundations of supervised machine learning (in Portuguese). The topics include: the geometry of the Hamming…

Dimensionality Reduction

The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline

2026-04-01 · Piyush Garg, Diana R. Gergel, Andrew E. Shao, Galen J. Yacalis arxiv

AI weather prediction has advanced rapidly, yet no unified mathematical framework explains what determines forecast skill. Existing theory addresses specific architectural choices rather than the learning pipeline as a w…