F
Frank Hutter
Researcher at University of Freiburg
Publications - 308
Citations - 42688
Frank Hutter is an academic researcher from University of Freiburg. The author has contributed to research in topics: Computer science & Hyperparameter optimization. The author has an hindex of 67, co-authored 255 publications receiving 27032 citations. Previous affiliations of Frank Hutter include University of Vermont & University of British Columbia.
Papers
More filters
Posted Content
Decoupled Weight Decay Regularization
Ilya Loshchilov,Frank Hutter +1 more
TL;DR: This work proposes a simple modification to recover the original formulation of weight decay regularization by decoupling the weight decay from the optimization steps taken w.r.t. the loss function, and provides empirical evidence that this modification substantially improves Adam's generalization performance.
Posted Content
SGDR: Stochastic Gradient Descent with Warm Restarts
Ilya Loshchilov,Frank Hutter +1 more
TL;DR: In this paper, a simple warm restart technique for stochastic gradient descent was proposed to improve its anytime performance when training deep neural networks, which achieved state-of-the-art results on both the CIFAR-10 and CifAR-100 datasets.
Book ChapterDOI
Sequential model-based optimization for general algorithm configuration
TL;DR: This paper extends the explicit regression models paradigm for the first time to general algorithm configuration problems, allowing many categorical parameters and optimization for sets of instances, and yields state-of-the-art performance.
Proceedings Article
Decoupled Weight Decay Regularization.
Ilya Loshchilov,Frank Hutter +1 more
TL;DR: Recently, this paper proposed a decoupled weight decay regularization that decouples the optimal weight decay factor from the setting of the learning rate for both standard SGD and Adam and substantially improves Adam's generalization performance.
Journal ArticleDOI
Deep learning with convolutional neural networks for EEG decoding and visualization.
Robin Tibor Schirrmeister,Jost Tobias Springenberg,Lukas D. J. Fiederer,Martin Glasstetter,Katharina Eggensperger,Michael Tangermann,Frank Hutter,Wolfram Burgard,Tonio Ball +8 more
TL;DR: This study shows how to design and train convolutional neural networks to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping.