Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Langer, Sophie"'
We study the generalization capabilities of Group Convolutional Neural Networks (GCNNs) with ReLU activation function by deriving upper and lower bounds for their Vapnik-Chervonenkis (VC) dimension. Specifically, we analyze how factors such as the nu
Externí odkaz:
http://arxiv.org/abs/2410.15800
Acceleration for non-convex functions has been an important problem in optimisation. We revisit star-convex functions, which are strictly unimodal on all lines through a minimizer. In [1], the authors accelerate gradient descent for star-convex funct
Externí odkaz:
http://arxiv.org/abs/2405.18976
Learning the Green's function using deep learning models enables to solve different classes of partial differential equations. A practical limitation of using deep learning for the Green's function is the repeated computationally expensive Monte-Carl
Externí odkaz:
http://arxiv.org/abs/2308.00350
We investigate the statistical behavior of gradient descent iterates with dropout in the linear regression model. In particular, non-asymptotic bounds for the convergence of expectations and covariance matrices of the iterates are derived. The result
Externí odkaz:
http://arxiv.org/abs/2306.10529
The recent statistical theory of neural networks focuses on nonparametric denoising problems that treat randomness as additive noise. Variability in image classification datasets does, however, not originate from additive noise but from variation of
Externí odkaz:
http://arxiv.org/abs/2206.02151
Autor:
Kohler, Michael, Langer, Sophie
Publikováno v:
In Journal of Statistical Planning and Inference January 2025 234
A successful mobile app monetization strategy is the foundation of any sustainable future business. App developers, in this regard, face the demanding challenge of building, maintaining and monetizing this strategy respectively. Factors, such as user
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-48944
Estimation of a regression function from independent and identically distributed data is considered. The $L_2$ error with integration with respect to the distribution of the predictor variable is used as the error criterion. The rate of convergence o
Externí odkaz:
http://arxiv.org/abs/2107.09532
In this paper we analyze the $L_2$ error of neural network regression estimates with one hidden layer. Under the assumption that the Fourier transform of the regression function decays suitably fast, we show that an estimate, where all initial weight
Externí odkaz:
http://arxiv.org/abs/2107.09550
Autor:
Kohler, Michael, Langer, Sophie
Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks. Nevertheless
Externí odkaz:
http://arxiv.org/abs/2011.13602