Well-tuned simple nets excel on tabular datasets
Tabular datasets are the last" unconquered castle" for deep learning, with traditional ML
methods like Gradient-Boosted Decision Trees still performing strongly even against recent …
methods like Gradient-Boosted Decision Trees still performing strongly even against recent …
Tree-structured parzen estimator: Understanding its algorithm components and their roles for better empirical performance
S Watanabe - arxiv preprint arxiv:2304.11127, 2023 - arxiv.org
Recent advances in many domains require more and more complicated experiment design.
Such complicated experiments often have many parameters, which necessitate parameter …
Such complicated experiments often have many parameters, which necessitate parameter …
Priorband: Practical hyperparameter optimization in the age of deep learning
Abstract Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream
performance. While a large number of methods for Hyperparameter Optimization (HPO) …
performance. While a large number of methods for Hyperparameter Optimization (HPO) …
Interpretable neural architecture search via bayesian optimisation with weisfeiler-lehman kernels
Current neural architecture search (NAS) strategies focus only on finding a single, good,
architecture. They offer little insight into why a specific network is performing well, or how we …
architecture. They offer little insight into why a specific network is performing well, or how we …
BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization
Bayesian optimization (BO) has become an established framework and popular tool for
hyperparameter optimization (HPO) of machine learning (ML) algorithms. While known for its …
hyperparameter optimization (HPO) of machine learning (ML) algorithms. While known for its …
Systematic design of Cauchy symmetric structures through Bayesian optimization
Abstract Using a new Bayesian Optimization algorithm to guide the design of mechanical
metamaterials, we design nonhomogeneous 3D structures possessing the Cauchy …
metamaterials, we design nonhomogeneous 3D structures possessing the Cauchy …
Joint entropy search for maximally-informed Bayesian optimization
Abstract Information-theoretic Bayesian optimization techniques have become popular for
optimizing expensive-to-evaluate black-box functions due to their non-myopic qualities …
optimizing expensive-to-evaluate black-box functions due to their non-myopic qualities …
Risk-averse heteroscedastic bayesian optimization
Many black-box optimization tasks arising in high-stakes applications require risk-averse
decisions. The standard Bayesian optimization (BO) paradigm, however, optimizes the …
decisions. The standard Bayesian optimization (BO) paradigm, however, optimizes the …
Achieving on-mobile real-time super-resolution with neural architecture and pruning search
Though recent years have witnessed remarkable progress in single image super-resolution
(SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep …
(SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep …
Provably efficient online hyperparameter optimization with population-based bandits
Many of the recent triumphs in machine learning are dependent on well-tuned
hyperparameters. This is particularly prominent in reinforcement learning (RL) where a small …
hyperparameters. This is particularly prominent in reinforcement learning (RL) where a small …