paper-with-me

Papers

Towards Robust and Automatic Hyper-Parameter Tunning

2021-11-28 · Mathieu Tuli, Mahdi S. Hosseini, Konstantinos N. Plataniotis

The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters simultaneously. In this work, we introduce a new class of HPO method and explore how the low-rank factorization of the convolutional weights of intermediate layers of a convolutional neural network can be used to define an analytical response surface for optimizing hyper-parameters, using only training data. We quantify how this surface behaves as a surrogate to model performance and can be solved using a trust-region search algorithm, which we call autoHyper. The algorithm outperforms state-of-the-art such as Bayesian Optimization and generalizes across model, optimizer, and dataset selection. Our code can be found at \url{https://github.com/MathieuTuli/autoHyper}.

📄 PDF Abstract BibTeX arXiv:2111.14056

Code (1)

mathieutuli/autohyper 공식 구현 pytorch

Tasks

Bayesian Optimization

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

From CDF to PDF --- A Density Estimation Method for High Dimensional Data

2018-04-15 · Shengdong Zhang

CDF2PDF is a method of PDF estimation by approximating CDF. The original idea of it was previously proposed in [1] called SIC. However, SIC requires additional hyper-parameter tunning, and no algorithms for computing hig…

Density Estimation

A Dynamic-Neighbor Particle Swarm Optimizer for Accurate Latent Factor Analysis

2023-02-23 · Jia Chen, Yixian Chun, Yuanyi Liu, Renyu Zhang 외

High-Dimensional and Incomplete matrices, which usually contain a large amount of valuable latent information, can be well represented by a Latent Factor Analysis model. The performance of an LFA model heavily rely on it…

Bayesian Low-rank Matrix Completion with Dual-graph Embedding: Prior Analysis and Tuning-free Inference

2022-03-18 · Yangge Chen, Lei Cheng, Yik-Chung Wu

Recently, there is a revival of interest in low-rank matrix completion-based unsupervised learning through the lens of dual-graph regularization, which has significantly improved the performance of multidisciplinary mach…

Graph EmbeddingImage InpaintingImputationLow-Rank Matrix Completion+3

Cluster-based Random Radial Basis Kernel Function for Hyperspectral Data Classification

2024-09-08 · Saeid Niazmardi

Kernel-based classification methods, particularly the support vector machine (SVM), are among the most common algorithms for hyperspectral data classification. The Radial Basis function (RBF) kernel has earned great popu…

Classification

Intelligent fault diagnosis of worm gearbox based on adaptive CNN using amended gorilla troop optimization with quantum gate mutation strategy

2024-03-19 · Govind Vashishtha, Sumika Chauhan, Surinder Kumar, Rajesh Kumar 외

The worm gearbox is a high-speed transmission system that plays a vital role in various industries. Therefore it becomes necessary to develop a robust fault diagnosis scheme for worm gearbox. Due to advancements in senso…

DiagnosticFault Diagnosis