
-
Squirrel: A Switching Hyperparameter Optimizer
In this short note, we describe our submission to the NeurIPS 2020 BBO c...
read it
-
Differential Evolution for Neural Architecture Search
Neural architecture search (NAS) methods rely on a search strategy for d...
read it
-
Convergence Analysis of Homotopy-SGD for non-convex optimization
First-order stochastic methods for solving large-scale non-convex optimi...
read it
-
Hyperparameter Transfer Across Developer Adjustments
After developer adjustments to a machine learning (ML) algorithm, how ca...
read it
-
On the Importance of Domain Model Configuration for Automated Planning Engines
The development of domain-independent planners within the AI Planning co...
read it
-
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
In this paper, we propose an approach to neural architecture search (NAS...
read it
-
Neural Model-based Optimization with Right-Censored Observations
In many fields of study, we only observe lower bounds on the true respon...
read it
-
Sample-Efficient Automated Deep Reinforcement Learning
Despite significant progress in challenging problems across various doma...
read it
-
NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search
Neural Architecture Search (NAS) is a logical next step in the automatic...
read it
-
Auto-Sklearn 2.0: The Next Generation
Automated Machine Learning, which supports practitioners and researchers...
read it
-
Prior-guided Bayesian Optimization
While Bayesian Optimization (BO) is a very popular method for optimizing...
read it
-
Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
While early AutoML frameworks focused on optimizing traditional ML pipel...
read it
-
Neural Ensemble Search for Performant and Calibrated Predictions
Ensembles of neural networks achieve superior performance compared to st...
read it
-
Learning Heuristic Selection with Dynamic Algorithm Configuration
A key challenge in satisfying planning is to use multiple heuristics wit...
read it
-
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Following early work on Hessian-free methods for deep learning, we study...
read it
-
Machine-Learning-Based Diagnostics of EEG Pathology
Machine learning (ML) methods have the potential to automate clinical EE...
read it
-
NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
One-shot neural architecture search (NAS) has played a crucial role in m...
read it
-
Meta-Learning of Neural Architectures for Few-Shot Learning
The recent progress in neural architectures search (NAS) has allowed sca...
read it
-
OpenML-Python: an extensible Python API for OpenML
OpenML is an online platform for open science collaboration in machine l...
read it
-
Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
Current Deep Reinforcement Learning algorithms still heavily rely on han...
read it
-
Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
We propose probabilistic models that can extrapolate learning curves of ...
read it
-
Understanding and Robustifying Differentiable Architecture Search
Differentiable Architecture Search (DARTS) has attracted a lot of attent...
read it
-
!MDP Playground: Meta-Features in Reinforcement Learning
Reinforcement Learning (RL) algorithms usually assume their environment ...
read it
-
Best Practices for Scientific Research on Neural Architecture Search
We describe a set of best practices for the young field of neural archit...
read it
-
Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
Bayesian Optimization (BO) is a common approach for hyperparameter optim...
read it
-
BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
Hyperparameter optimization and neural architecture search can become pr...
read it
-
Towards White-box Benchmarks for Algorithm Control
The performance of many algorithms in the fields of hard combinatorial p...
read it
-
Meta-Surrogate Benchmarking for Hyperparameter Optimization
Despite the recent progress in hyperparameter optimization (HPO), availa...
read it
-
AutoDispNet: Improving Disparity Estimation with AutoML
Much research work in computer vision is being spent on optimizing exist...
read it
-
Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization
Due to the high computational demands executing a rigorous comparison be...
read it
-
Meta-Learning Acquisition Functions for Bayesian Optimization
Many practical applications of machine learning require data-efficient b...
read it
-
NAS-Bench-101: Towards Reproducible Neural Architecture Search
Recent advances in neural architecture search (NAS) demand tremendous co...
read it
-
Learning to Design RNA
Designing RNA molecules has garnered recent interest in medicine, synthe...
read it
-
Neural Architecture Search: A Survey
Deep Learning has enabled remarkable progress over the last years on a v...
read it
-
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
While existing work on neural architecture search (NAS) tunes hyperparam...
read it
-
BOHB: Robust and Efficient Hyperparameter Optimization at Scale
Modern deep learning methods are very sensitive to many hyperparameters,...
read it
-
Generative Reversible Networks
Generative models with an encoding component such as autoencoders curren...
read it
-
Training Generative Reversible Networks
Generative models with an encoding component such as autoencoders curren...
read it
-
Maximizing acquisition functions for Bayesian optimization
Bayesian optimization is a sample-efficient approach to global optimizat...
read it
-
Multi-objective Architecture Search for CNNs
Architecture search aims at automatically finding neural architectures t...
read it
-
Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari
Evolution Strategies (ES) have recently been demonstrated to be a viable...
read it
-
Uncertainty Estimates for Optical Flow with Multi-Hypotheses Networks
Recent work has shown that optical flow estimation can be formulated as ...
read it
-
The reparameterization trick for acquisition functions
Bayesian optimization is a sample-efficient approach to solving global o...
read it
-
Fixing Weight Decay Regularization in Adam
We note that common implementations of adaptive gradient algorithms, suc...
read it
-
Simple And Efficient Architecture Search for Convolutional Neural Networks
Neural networks have recently had a lot of success for many tasks. Howev...
read it
-
Predicting Runtime Distributions using Deep Neural Networks
Many state-of-the-art algorithms for solving hard combinatorial problems...
read it
-
Warmstarting of Model-based Algorithm Configuration
The performance of many hard combinatorial problem solvers depends stron...
read it
-
Deep learning with convolutional neural networks for decoding and visualization of EEG pathology
We apply convolutional neural networks (ConvNets) to the task of disting...
read it
-
OpenML Benchmarking Suites and the OpenML100
We advocate the use of curated, comprehensive benchmark suites of machin...
read it
-
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
The original ImageNet dataset is a popular large-scale benchmark for tra...
read it