Data-Driven Methods for Modelling and Optimizing the Empirical Performance of Deep Neural Networks

Hyperparameter Transfer Across Developer Adjustments

Autori: Danny Stoll, Jörg Franke, Diane Wagner, Simon Selg, Frank Hutter
Pubblicato in: NeurIPS MetaLearning Workshop, 2020
Editore: online

Multi-headed Neural Ensemble Search

Autori: Ashwin Raaghav Narayanan, Arber Zela, Tonmoy Saikia, Thomas Brox, Frank Hutter
Pubblicato in: ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021
Editore: online

Transferring Optimally Across Data Distributions via Homotopy Methods

Autori: Matilde Gargiani, Andrea Zanelli, Quoc Tran Dinh, Moritz Diehl, Frank Hutter
Pubblicato in: ICLR 2020, 2020
Editore: online

NAS-Bench-x11 and the Power of Learning Curves

Autori: Shen Yan, Colin White, Yash Savani, Frank Hutter
Pubblicato in: NeurIPS 2021, 2021
Editore: online

Meta-Learning of Neural Architectures for Few-Shot Learning

Autori: Thomas Elsken, Benedikt Staffler, Jan Hendrik Metzen, Frank Hutter
Pubblicato in: CVPR 2020, 2020
Editore: IEEE

OpenML Benchmarking Suites

Autori: Bernd Bischl, Giuseppe Casalicchio, Matthias Feurer, Pieter Gijsbers, Frank Hutter, Michel Lang, Rafael Gomes Mantovani, Jan van Rijn, Joaquin Vanschoren
Pubblicato in: NeurIPS Datasets and Benchmarks 2021, 2021
Editore: online

Sample-Efficient Automated Deep Reinforcement Learning

Autori: Jörg Franke, Gregor Köhler, André Biedenkapp, Frank Hutter
Pubblicato in: ICLR 2021, 2021
Editore: online

Understanding and Robustifying Differentiable Architecture Search

Autori: Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, Frank Hutter
Pubblicato in: ICLR 2020, 2020
Editore: online

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Autori: Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra
Pubblicato in: AISTATS 2021, 2021
Editore: Proceedings of Machine Learning Research

Combining Hyperband and Bayesian Optimization

Autori: Stefan Falkner, Aaron Klein, Frank Hutter
Pubblicato in: Proceedings of BayesOpt 2017, 2017
Editore: published online

Learning curve predictionwith bayesian neural networks

Autori: Aaron Klein, Stefan Falkner, Jost Tobias Springenberg, Frank Hutter
Pubblicato in: proceedings of ICLR, 2017
Editore: published online

RoBO: A Flexible and Robust Bayesian Optimization Framework in Python

Autori: Aaron Klein, Stefan Falkner, Numair Mansur, Frank Hutter
Pubblicato in: Proceedings of BayesOpt 2017, 2017
Editore: published online

The Sacred Infrastructure for Computational Research

Autori: Klaus Greff, Aaron Klein, Martin Chovanec, Frank Hutter, Jürgen Schmidhuber
Pubblicato in: proceedings of the 15th python in science conference, 2017
Editore: published online

An Empirical Study of Hyperparameter Importance Across Datasets

Autori: Jan N. van Rijn, Frank Hutter
Pubblicato in: proceedings of AutoML, 2017
Editore: published online

The reparameterization trick for acquisition functions

Autori: James T. Wilson, Riccardo Moriconi, Frank Hutter, Marc Peter Deisenroth
Pubblicato in: Proceedings of BayesOpt 2017, 2017
Editore: published online

BOHB: Robust and Efficient Hyperparameter Optimization at Scale

Autori: Falkner, Stefan; Klein, Aaron; Hutter, Frank
Pubblicato in: ICML 2018, Numero 5, 2018
Editore: ICML

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

Autori: Zela, Arber; Klein, Aaron; Falkner, Stefan; Hutter, Frank
Pubblicato in: AutoML Workshop, Numero 1, 2018
Editore: AutoML

Maximizing acquisition functions for Bayesian optimization

Autori: Wilson, James T.; Hutter, Frank; Deisenroth, Marc Peter
Pubblicato in: NeurIPS 2018, Numero 1, 2018
Editore: NeurIPS

Hyperparameter Importance Across Datasets

Autori: Jan N. van Rijn, Frank Hutter
Pubblicato in: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18, 2018, Pagina/e 2367-2376, ISBN 9781-450355520
Editore: ACM Press
DOI: 10.1145/3219819.3220058

Decoupled Weight Decay Regularization

Autori: Loshchilov, Ilya; Hutter, Frank
Pubblicato in: ICLR 2019, Numero 5, 2019
Editore: ICLR

Learning to Design RNA

Autori: Runge, Frederic; Stoll, Danny; Falkner, Stefan; Hutter, Frank
Pubblicato in: ICLR 2019, Numero 5, 2019
Editore: ICLR

Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari

Autori: Chrabaszcz, Patryk; Loshchilov, Ilya; Hutter, Frank
Pubblicato in: IJCAI 2018, Numero 1, 2018
Editore: IJCAI

NAS-Bench-101: Towards Reproducible Neural Architecture Search

Autori: Ying, Chris; Klein, Aaron; Real, Esteban; Christiansen, Eric; Murphy, Kevin; Hutter, Frank
Pubblicato in: ICML 2019, Numero 5, 2019
Editore: ICML

Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution - Published as a conference paper at ICLR 2019

Autori: Hutter, Frank Elsken, Thomas Metzen, Jan Hendrik
Pubblicato in: 2019
Editore: open review

Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

Autori: Matilde Gargiani, Aaron Klein, Stefan Falkner, Frank Hutter
Pubblicato in: 2019
Editore: online

Practical Automated Machine Learning for the AutoML Challenge 2018

Autori: Matthias Feurer Katharina Eggensperger Stefan Falkner Marius Lindauer Frank Hutter
Pubblicato in: ICML 2018, 2018
Editore: Online

Towards Further Automation in AutoML

Autori: Matthias Feurer Frank Hutter
Pubblicato in: ICML 2018 workshop on AutoML, 2018
Editore: Online

Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control

Autori: Jör Franke, Jörg Gregor Köhler Noor Awad Frank Hutter
Pubblicato in: NeurIPS 2019, 2019
Editore: Online

Bag of Tricks for Neural Architecture Search

Autori: Thomas Elsken, Benedikt Staffler, Arber Zela, Jan Hendrik Metzen, Frank Hutter
Pubblicato in: CVPR 2021 Workshop on Neural Architecture Search, 2021
Editore: online

HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO

Autori: Katharina Eggensperger, Philipp Müller, Neeratyoy Mallik, Matthias Feurer, Rene Sass, Aaron Klein, Noor Awad, Marius Lindauer, Frank Hutter
Pubblicato in: NeurIPS Datasets and Benchmarks 2021, 2021
Editore: online

TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation

Autori: Samuel G. Müller, Frank Hutter
Pubblicato in: ICCV 2021, 2021
Editore: online

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search

Autori: Arber Zela, Julien Siems, Frank Hutter
Pubblicato in: ICLR 2020, 2020
Editore: online

Bayesian Optimization with a Prior for the Optimum

Autori: Artur Souza, Luigi Nardi, Leonardo B. Oliveira,Kunle Olukotun, Marius Lindauer, Frank Hutte
Pubblicato in: ECML PKDD 2021, 2021
Editore: online

Neural Ensemble Search for Uncertainty Estimation and Dataset Shift

Autori: Sheheryar Zaidi, Arber Zela, Thomas Elsken, Chris C Holmes, Frank Hutter, Yee Teh
Pubblicato in: NeurIPS 2021, 2021
Editore: online

How Powerful are Performance Predictors in Neural Architecture Search?

Autori: Colin White, Arber Zela, Robin Ru, Yang Liu, Frank Hutter
Pubblicato in: NeurIPS 2021, 2021
Editore: online

Well-tuned Simple Nets Excel on Tabular Datasets

Autori: Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka
Pubblicato in: NeurIPS 2021, 2021
Editore: online

MDP Playground: A Design and Debug Testbed for Reinforcement Learning

Autori: Rajan, Raghu; Diaz, Jessica Lizeth Borja; Guttikonda, Suresh; Ferreira, Fabio; Biedenkapp, André; von Hartz, Jan Ole; Hutter, Frank
Pubblicato in: arXiv preprint, Numero 17, 2021
Editore: online

On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

Autori: Matilde Gargiani, Andrea Zanelli, Moritz Diehl, Frank Hutter
Pubblicato in: 2020
Editore: online

OpenML Benchmarking Suites and the OpenML100

Autori: Bischl, Bernd; Casalicchio, Giuseppe; Feurer, Matthias; Hutter, Frank; Lang, Michel; Mantovani, Rafael G.; van Rijn, Jan N.; Vanschoren, Joaquin
Pubblicato in: Numero 1, 2017
Editore: arXiv

A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

Autori: Chrabaszcz, Patryk; Loshchilov, Ilya; Hutter, Frank
Pubblicato in: arXiv, Numero 5, 2017
Editore: arXiv

Neural Model-based Optimization with Right-Censored Observations

Autori: Katharina Eggensperger, Kai Haase, Philipp Müller, Marius Lindauer, Frank Hutter
Pubblicato in: arXiv, 2020
Editore: online

Auto-sklearn 2.0: The Next Generation

Autori: Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter
Pubblicato in: arXiv, 2020
Editore: online

Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning

Autori: Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter
Pubblicato in: arXiv, 2021
Editore: online

Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

Autori: Lucas Zimmer, Marius Lindauer, Frank Hutter
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero pp. 3079-3090, vol. 43, 2021, ISSN 1939-3539
Editore: IEEE Computer Society
DOI: 10.1109/tpami.2021.3067763

Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

Autori: Zimmer, Lucas; Lindauer, Marius; Hutter, Frank
Pubblicato in: TPAMI, Numero 6, 2021, ISSN 2160-9292
Editore: IEEE Computer Society

Neural Architecture Search: A Survey

Autori: Elsken, Thomas; Metzen, Jan Hendrik; Hutter, Frank
Pubblicato in: JMLR, Numero 5, 2019, ISSN 1533-7928
Editore: JMLR

Fast Bayesian hyperparameteroptimization on large datasets

Autori: Aaron Klein Stefan Falkner Simon Bartels Philipp Hennig Frank Hutter
Pubblicato in: Electronic Journal of Statistics, 2017, ISSN 1935-7524
Editore: Institute of Mathematical Statistics

SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization

Autori: Marius Lindauer, Katharina Eggensperger, Matthias Feurer, Andre Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, Rene Sass, Frank Hutter
Pubblicato in: Journal of Machine Learning Research, Numero 23, 2022, ISSN 1533-7928
Editore: online

Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019

Autori: Zhengying Liu, Adrien Pavao, Zhen Xu, Sergio Escalera, Fabio Ferreira, Isabelle Guyon, Sirui Hong, Frank Hutter, Rongrong Ji, Julio C. S. Jacques Junior, Ge Li, Marius Lindauer, Zhipeng Luo, Meysam Madadi, Thomas Nierhoff, Kangning Niu, Chunguang Pan, Danny Stoll, Sebastien Treguer, Jin Wang, Peng Wang, Chenglin Wu, Youcheng Xiong, Arber Zela, Yang Zhang
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 43/9, 2021, Pagina/e 3108-3125, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2021.3075372

Uncertainty Estimates and Multi-hypotheses Networks for Optical Flow

Autori: Eddy Ilg, Özgün Çiçek, Silvio Galesso, Aaron Klein, Osama Makansi, Frank Hutter, Thomas Brox
Pubblicato in: Computer Vision – ECCV 2018 - 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII, Numero 11211, 2018, Pagina/e 677-693, ISBN 978-3-030-01233-5
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-01234-2_40

Automated Machine Learning: Methods, Systems, Challenges

Autori: Hutter, Frank, Kotthoff, Lars, Vanschoren, Joaquin (Eds.)
Pubblicato in: The Springer Series on Challenges in Machine Learning, 2019
Editore: Springer Switzerland

Pubblicazioni

Condividi questa pagina

Scarica