paper-with-me

홈 › Papers

Exponential Error Convergence in Data Classification with Optimized Random Features: Acceleration by Quantum Machine Learning

2021-06-16 · Hayata Yamasaki, Sho Sonoda

Classification is a common task in machine learning. Random features (RFs) stand as a central technique for scalable learning algorithms based on kernel methods, and more recently proposed optimized random features, sampled depending on the model and the data distribution, can significantly reduce and provably minimize the required number of features. However, existing research on classification using optimized RFs has suffered from computational hardness in sampling each optimized RF; moreover, it has failed to achieve the exponentially fast error-convergence speed that other state-of-the-art kernel methods can achieve under a low-noise condition. To overcome these slowdowns, we here construct a classification algorithm with optimized RFs accelerated by means of quantum machine learning (QML) and study its runtime to clarify overall advantage. We prove that our algorithm can achieve the exponential error convergence under the low-noise condition even with optimized RFs; at the same time, our algorithm can exploit the advantage of the significant reduction of the number of features without the computational hardness owing to QML. These results discover a promising application of QML to acceleration of the leading kernel-based classification algorithm without ruining its wide applicability and the exponential error-convergence speed.

📄 PDF Abstract BibTeX arXiv:2106.09028

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningClassificationQuantum Machine Learning

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Exponential convergence of testing error for stochastic gradient methods

2017-12-13 · Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach

We consider binary classification problems with positive definite kernels and square loss, and study the convergence rates of stochastic gradient methods. We show that while the excess testing loss (squared loss) converg…

Binary ClassificationClassificationGeneral Classification

Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors

2018-06-14 · Atsushi Nitanda, Taiji Suzuki

We consider stochastic gradient descent and its averaging variant for binary classification problems in a reproducing kernel Hilbert space. In the traditional analysis using a consistency property of loss functions, it i…

Binary ClassificationClassificationGeneral Classification

Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features

2019-11-13 · Shingo Yashima, Atsushi Nitanda, Taiji Suzuki

Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to…

Binary ClassificationClassificationGeneral Classification

An optimal scheduled learning rate for a randomized Kaczmarz algorithm

2022-02-24 · Nicholas F. Marshall, Oscar Mickelin

We study how the learning rate affects the performance of a relaxed randomized Kaczmarz algorithm for solving $A x \approx b + \varepsilon$, where $A x =b$ is a consistent linear system and $\varepsilon$ has independent …

Multiclass learning with margin: exponential rates with no bias-variance trade-off

2022-02-03 · Stefano Vigogna, Giacomo Meanti, Ernesto de Vito, Lorenzo Rosasco

We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponenti…

Classification