{"list":"other","total":84,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"2003.06505","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","created":"2020-03-13","cited_by_count":383},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1502.07943","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","created":"2015-02-27","cited_by_count":221},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1301.1942","title":"Bayesian Optimization in a Billion Dimensions via Random Embeddings","created":"2013-01-09","cited_by_count":182},{"id":"2007.15745","title":"On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice","created":"2020-07-30","cited_by_count":182},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1508.04409","title":"ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R","created":"2015-08-18","cited_by_count":172},{"id":"1806.10282","title":"Auto-Keras: An Efficient Neural Architecture Search System","created":"2018-06-27","cited_by_count":171},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1610.08733","title":"GPflow: A Gaussian process library using TensorFlow","created":"2016-10-27","cited_by_count":140},{"id":"1503.01673","title":"High Dimensional Bayesian Optimisation and Bandits via Additive Models","created":"2015-03-05","cited_by_count":139},{"id":"1603.08785","title":"COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting","created":"2016-03-29","cited_by_count":138},{"id":"1605.07079","title":"Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets","created":"2016-05-23","cited_by_count":132},{"id":"2003.05689","title":"Hyper-Parameter Optimization: A Review of Algorithms and Applications","created":"2020-03-12","cited_by_count":114},{"id":"1403.5607","title":"Bayesian Optimization with Unknown Constraints","created":"2014-03-22","cited_by_count":109},{"id":"1802.09596","title":"Tunability: Importance of Hyperparameters of Machine Learning Algorithms","created":"2018-02-26","cited_by_count":99},{"id":"1406.3896","title":"Freeze-Thaw Bayesian Optimization","created":"2014-06-16","cited_by_count":90},{"id":"1401.3492","title":"ParamILS: An Automatic Algorithm Configuration Framework","created":"2014-01-15","cited_by_count":89},{"id":"1511.05467","title":"Predictive Entropy Search for Multi-objective Bayesian Optimization","created":"2015-11-17","cited_by_count":88},{"id":"1804.03515","title":"Hyperparameters and Tuning Strategies for Random Forest","created":"2018-04-10","cited_by_count":84},{"id":"1603.06212","title":"Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science","created":"2016-03-20","cited_by_count":75},{"id":"2106.06257","title":"HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML","created":"2021-06-11","cited_by_count":75},{"id":"1911.11090","title":"Meta-Learning of Neural Architectures for Few-Shot Learning","created":"2019-11-25","cited_by_count":73},{"id":"2101.07667","title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","created":"2021-01-19","cited_by_count":71},{"id":"1402.0929","title":"Input Warping for Bayesian Optimization of Non-stationary Functions","created":"2014-02-05","cited_by_count":67},{"id":"1903.06694","title":"Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly","created":"2019-03-15","cited_by_count":67},{"id":"2006.13799","title":"Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL","created":"2020-06-24","cited_by_count":67},{"id":"1706.03673","title":"Dealing with Integer-valued Variables in Bayesian Optimization with Gaussian Processes","created":"2017-06-12","cited_by_count":66},{"id":"1806.01619","title":"BOCK : Bayesian Optimization with Cylindrical Kernels","created":"2018-06-05","cited_by_count":65},{"id":"1710.04725","title":"Hyperparameter Importance Across Datasets","created":"2017-10-12","cited_by_count":63},{"id":"2002.02518","title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","created":"2020-02-06","cited_by_count":63},{"id":"1909.02453","title":"Best Practices for Scientific Research on Neural Architecture Search","created":"2019-09-05","cited_by_count":54},{"id":"1911.12809","title":"Greed is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisation","created":"2019-11-28","cited_by_count":51},{"id":"1909.12552","title":"Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning","created":"2019-09-27","cited_by_count":50},{"id":"2106.00421","title":"OpenBox: A Generalized Black-box Optimization Service","created":"2021-06-01","cited_by_count":46},{"id":"2103.00742","title":"Automated Machine Learning on Graphs: A Survey","created":"2021-03-01","cited_by_count":39},{"id":"1807.06906","title":"Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search","created":"2018-07-18","cited_by_count":38},{"id":"1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","created":"2015-06-08","cited_by_count":37},{"id":"2001.06509","title":"Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems","created":"2020-01-17","cited_by_count":36},{"id":"1810.05236","title":"Practical Design Space Exploration","created":"2018-10-11","cited_by_count":35},{"id":"1705.05654","title":"To tune or not to tune the number of trees in random forest?","created":"2017-05-16","cited_by_count":33},{"id":"1906.02287","title":"Automated Machine Learning: State-of-The-Art and Open Challenges","created":"2019-06-05","cited_by_count":29},{"id":"1609.01051","title":"Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints","created":"2016-09-05","cited_by_count":27},{"id":"2006.14284","title":"Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation","created":"2020-06-25","cited_by_count":27},{"id":"1705.06058","title":"Pitfalls and Best Practices in Algorithm Configuration","created":"2017-05-17","cited_by_count":25},{"id":"2007.14166","title":"A Comparison of Optimization Algorithms for Deep Learning","created":"2020-07-28","cited_by_count":23},{"id":"1902.01894","title":"A Generalized Framework for Population Based Training","created":"2019-02-05","cited_by_count":22},{"id":"1904.03867","title":"Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability","created":"2019-04-08","cited_by_count":22},{"id":"2006.08246","title":"Learning Heuristic Selection with Dynamic Algorithm Configuration","created":"2020-06-15","cited_by_count":21},{"id":"2104.00629","title":"Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features","created":"2021-04-01","cited_by_count":21},{"id":"1709.04636","title":"Warmstarting of Model-based Algorithm Configuration","created":"2017-09-14","cited_by_count":17},{"id":"1905.12982","title":"Meta-Surrogate Benchmarking for Hyperparameter Optimization","created":"2019-05-30","cited_by_count":17},{"id":"1409.4011","title":"Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces","created":"2014-09-14","cited_by_count":16},{"id":"1703.03373","title":"mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions","created":"2017-03-09","cited_by_count":16},{"id":"1811.09409","title":"Learning Multiple Defaults for Machine Learning Algorithms","created":"2018-11-23","cited_by_count":10},{"id":"2003.13826","title":"Initial Design Strategies and their Effects on Sequential Model-Based Optimization","created":"2020-03-30","cited_by_count":10},{"id":"2008.00553","title":"A Unifying Framework for Parallel and Distributed Processing in R using Futures","created":"2020-08-02","cited_by_count":9},{"id":"2007.02837","title":"Does imputation matter? Benchmark for predictive models","created":"2020-07-06","cited_by_count":7},{"id":"1701.05936","title":"The biglasso Package: A Memory- and Computation-Efficient Solver for Lasso Model Fitting with Big Data in R","created":"2017-01-20","cited_by_count":6},{"id":"1807.01279","title":"Dynamic Control of Explore/Exploit Trade-Off In Bayesian Optimization","created":"2018-07-03","cited_by_count":5},{"id":"1405.6974","title":"Futility Analysis in the Cross-Validation of Machine Learning Models","created":"2014-05-27","cited_by_count":4},{"id":"2106.05767","title":"Meta-Learning for Symbolic Hyperparameter Defaults","created":"2021-06-10","cited_by_count":4}],"next_cursor":null}