Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Frank Hutter

Frank Hutter

Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization


May 03, 2021
Julia Guerrero-Viu, Sven Hauns, Sergio Izquierdo, Guilherme Miotto, Simon Schrodi, Andre Biedenkapp, Thomas Elsken, Difan Deng, Marius Lindauer, Frank Hutter

Figure 1 for Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
Figure 2 for Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
Figure 3 for Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
Figure 4 for Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization

  Access Paper or Ask Questions

How Powerful are Performance Predictors in Neural Architecture Search?


Apr 02, 2021
Colin White, Arber Zela, Binxin Ru, Yang Liu, Frank Hutter

Figure 1 for How Powerful are Performance Predictors in Neural Architecture Search?
Figure 2 for How Powerful are Performance Predictors in Neural Architecture Search?
Figure 3 for How Powerful are Performance Predictors in Neural Architecture Search?
Figure 4 for How Powerful are Performance Predictors in Neural Architecture Search?

  Access Paper or Ask Questions

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


Mar 18, 2021
Samuel G. Müller, Frank Hutter

Figure 1 for TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
Figure 2 for TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
Figure 3 for TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
Figure 4 for TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation

  Access Paper or Ask Questions

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


Feb 26, 2021
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra

Figure 1 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 2 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 3 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 4 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
* 19 pages, accepted by AISTATS 2021 
  Access Paper or Ask Questions

Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies


Feb 08, 2021
Fabio Ferreira, Thomas Nierhoff, Frank Hutter

Figure 1 for Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies
Figure 2 for Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies
Figure 3 for Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies
Figure 4 for Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies
* AAAI 2021 Meta-Learning Workshop 
  Access Paper or Ask Questions

In-Loop Meta-Learning with Gradient-Alignment Reward


Feb 05, 2021
Samuel Müller, André Biedenkapp, Frank Hutter

Figure 1 for In-Loop Meta-Learning with Gradient-Alignment Reward
Figure 2 for In-Loop Meta-Learning with Gradient-Alignment Reward
Figure 3 for In-Loop Meta-Learning with Gradient-Alignment Reward
Figure 4 for In-Loop Meta-Learning with Gradient-Alignment Reward
* Accepted to Meta Learning Workshop at AAAI 
  Access Paper or Ask Questions

Squirrel: A Switching Hyperparameter Optimizer


Dec 16, 2020
Noor Awad, Gresa Shala, Difan Deng, Neeratyoy Mallik, Matthias Feurer, Katharina Eggensperger, Andre' Biedenkapp, Diederick Vermetten, Hao Wang, Carola Doerr, Marius Lindauer, Frank Hutter


  Access Paper or Ask Questions

Differential Evolution for Neural Architecture Search


Dec 11, 2020
Noor Awad, Neeratyoy Mallik, Frank Hutter

Figure 1 for Differential Evolution for Neural Architecture Search
Figure 2 for Differential Evolution for Neural Architecture Search
Figure 3 for Differential Evolution for Neural Architecture Search
Figure 4 for Differential Evolution for Neural Architecture Search

  Access Paper or Ask Questions

Convergence Analysis of Homotopy-SGD for non-convex optimization


Nov 20, 2020
Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh, Moritz Diehl, Frank Hutter

Figure 1 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 2 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 3 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 4 for Convergence Analysis of Homotopy-SGD for non-convex optimization
* 21 pages, 14 figures, technical report 
  Access Paper or Ask Questions

Hyperparameter Transfer Across Developer Adjustments


Oct 25, 2020
Danny Stoll, Jörg K. H. Franke, Diane Wagner, Simon Selg, Frank Hutter

Figure 1 for Hyperparameter Transfer Across Developer Adjustments
Figure 2 for Hyperparameter Transfer Across Developer Adjustments
Figure 3 for Hyperparameter Transfer Across Developer Adjustments
Figure 4 for Hyperparameter Transfer Across Developer Adjustments

  Access Paper or Ask Questions

On the Importance of Domain Model Configuration for Automated Planning Engines


Oct 15, 2020
Mauro Vallati, Lukas Chrpa, Thomas L. McCluskey, Frank Hutter

Figure 1 for On the Importance of Domain Model Configuration for Automated Planning Engines
Figure 2 for On the Importance of Domain Model Configuration for Automated Planning Engines
Figure 3 for On the Importance of Domain Model Configuration for Automated Planning Engines
Figure 4 for On the Importance of Domain Model Configuration for Automated Planning Engines
* Under consideration in Journal of Automated Reasoning 
  Access Paper or Ask Questions

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search


Oct 09, 2020
Jovita Lukasik, David Friede, Arber Zela, Heiner Stuckenschmidt, Frank Hutter, Margret Keuper

Figure 1 for Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Figure 2 for Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Figure 3 for Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Figure 4 for Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
* 13 pages, 4 figures, 6 tables 
  Access Paper or Ask Questions

Sample-Efficient Automated Deep Reinforcement Learning


Oct 05, 2020
Jörg K. H. Franke, Gregor Köhler, André Biedenkapp, Frank Hutter

Figure 1 for Sample-Efficient Automated Deep Reinforcement Learning
Figure 2 for Sample-Efficient Automated Deep Reinforcement Learning
Figure 3 for Sample-Efficient Automated Deep Reinforcement Learning
Figure 4 for Sample-Efficient Automated Deep Reinforcement Learning

  Access Paper or Ask Questions

Neural Model-based Optimization with Right-Censored Observations


Sep 29, 2020
Katharina Eggensperger, Kai Haase, Philipp Müller, Marius Lindauer, Frank Hutter

Figure 1 for Neural Model-based Optimization with Right-Censored Observations
Figure 2 for Neural Model-based Optimization with Right-Censored Observations
Figure 3 for Neural Model-based Optimization with Right-Censored Observations
Figure 4 for Neural Model-based Optimization with Right-Censored Observations

  Access Paper or Ask Questions

NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search


Aug 22, 2020
Julien Siems, Lucas Zimmer, Arber Zela, Jovita Lukasik, Margret Keuper, Frank Hutter

Figure 1 for NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search
Figure 2 for NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search
Figure 3 for NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search
Figure 4 for NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search

  Access Paper or Ask Questions

Auto-Sklearn 2.0: The Next Generation


Jul 08, 2020
Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter

Figure 1 for Auto-Sklearn 2.0: The Next Generation
Figure 2 for Auto-Sklearn 2.0: The Next Generation
Figure 3 for Auto-Sklearn 2.0: The Next Generation
Figure 4 for Auto-Sklearn 2.0: The Next Generation

  Access Paper or Ask Questions

Prior-guided Bayesian Optimization


Jun 25, 2020
Artur Souza, Luigi Nardi, Leonardo B. Oliveira, Kunle Olukotun, Marius Lindauer, Frank Hutter

Figure 1 for Prior-guided Bayesian Optimization
Figure 2 for Prior-guided Bayesian Optimization
Figure 3 for Prior-guided Bayesian Optimization
Figure 4 for Prior-guided Bayesian Optimization

  Access Paper or Ask Questions

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


Jun 24, 2020
Lucas Zimmer, Marius Lindauer, Frank Hutter

Figure 1 for Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
Figure 2 for Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
Figure 3 for Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
Figure 4 for Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

  Access Paper or Ask Questions

Neural Ensemble Search for Performant and Calibrated Predictions


Jun 15, 2020
Sheheryar Zaidi, Arber Zela, Thomas Elsken, Chris Holmes, Frank Hutter, Yee Whye Teh

Figure 1 for Neural Ensemble Search for Performant and Calibrated Predictions
Figure 2 for Neural Ensemble Search for Performant and Calibrated Predictions
Figure 3 for Neural Ensemble Search for Performant and Calibrated Predictions
Figure 4 for Neural Ensemble Search for Performant and Calibrated Predictions

  Access Paper or Ask Questions

Learning Heuristic Selection with Dynamic Algorithm Configuration


Jun 15, 2020
David Speck, André Biedenkapp, Frank Hutter, Robert Mattmüller, Marius Lindauer

Figure 1 for Learning Heuristic Selection with Dynamic Algorithm Configuration
Figure 2 for Learning Heuristic Selection with Dynamic Algorithm Configuration
Figure 3 for Learning Heuristic Selection with Dynamic Algorithm Configuration
Figure 4 for Learning Heuristic Selection with Dynamic Algorithm Configuration
* 9 pages, 4 figures, 3 tables 
  Access Paper or Ask Questions

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


Jun 09, 2020
Matilde Gargiani, Andrea Zanelli, Moritz Diehl, Frank Hutter

Figure 1 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 2 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 3 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 4 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

  Access Paper or Ask Questions

Machine-Learning-Based Diagnostics of EEG Pathology


Feb 11, 2020
Lukas Alexander Wilhelm Gemein, Robin Tibor Schirrmeister, Patryk ChrabÄ…szcz, Daniel Wilson, Joschka Boedecker, Andreas Schulze-Bonhage, Frank Hutter, Tonio Ball

Figure 1 for Machine-Learning-Based Diagnostics of EEG Pathology
Figure 2 for Machine-Learning-Based Diagnostics of EEG Pathology
Figure 3 for Machine-Learning-Based Diagnostics of EEG Pathology
Figure 4 for Machine-Learning-Based Diagnostics of EEG Pathology

  Access Paper or Ask Questions

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


Jan 28, 2020
Arber Zela, Julien Siems, Frank Hutter

Figure 1 for NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
Figure 2 for NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
Figure 3 for NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
Figure 4 for NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
* In: International Conference on Learning Representations (ICLR 2020); 20 pages, 20 figures 
  Access Paper or Ask Questions

Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control


Dec 04, 2019
Jörg K. H. Franke, Gregor Köhler, Noor Awad, Frank Hutter

Figure 1 for Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
Figure 2 for Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
Figure 3 for Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
Figure 4 for Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
* NeurIPS 2019 MetaLearn Workshop 
  Access Paper or Ask Questions

Meta-Learning of Neural Architectures for Few-Shot Learning


Nov 25, 2019
Thomas Elsken, Benedikt Staffler, Jan Hendrik Metzen, Frank Hutter

Figure 1 for Meta-Learning of Neural Architectures for Few-Shot Learning
Figure 2 for Meta-Learning of Neural Architectures for Few-Shot Learning
Figure 3 for Meta-Learning of Neural Architectures for Few-Shot Learning
Figure 4 for Meta-Learning of Neural Architectures for Few-Shot Learning

  Access Paper or Ask Questions

OpenML-Python: an extensible Python API for OpenML


Nov 06, 2019
Matthias Feurer, Jan N. van Rijn, Arlind Kadra, Pieter Gijsbers, Neeratyoy Mallik, Sahithya Ravi, Andreas Müller, Joaquin Vanschoren, Frank Hutter

Figure 1 for OpenML-Python: an extensible Python API for OpenML

  Access Paper or Ask Questions