{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1506.01186","title":"Cyclical Learning Rates for Training Neural Networks","created":"2015-06-03","cited_by_count":629},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208},{"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":"1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","created":"2017-03-14","cited_by_count":118},{"id":"1811.11597","title":"Automated Algorithm Selection: Survey and Perspectives","created":"2018-11-28","cited_by_count":114},{"id":"1802.09596","title":"Tunability: Importance of Hyperparameters of Machine Learning Algorithms","created":"2018-02-26","cited_by_count":99},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"1401.3492","title":"ParamILS: An Automatic Algorithm Configuration Framework","created":"2014-01-15","cited_by_count":89},{"id":"1709.07417","title":"Neural Optimizer Search with Reinforcement Learning","created":"2017-09-21","cited_by_count":82},{"id":"2204.11051","title":"$\\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization","created":"2022-04-23","cited_by_count":70},{"id":"1710.04725","title":"Hyperparameter Importance Across Datasets","created":"2017-10-12","cited_by_count":63},{"id":"2009.11243","title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves","created":"2020-09-23","cited_by_count":58},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"2004.11812","title":"Self-Paced Deep Reinforcement Learning","created":"2020-04-24","cited_by_count":50},{"id":"1905.08006","title":"Deep Reinforcement Learning Based Parameter Control in Differential Evolution","created":"2019-05-20","cited_by_count":38},{"id":"1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","created":"2015-06-08","cited_by_count":37},{"id":"2107.10847","title":"Accelerating Quadratic Optimization with Reinforcement Learning","created":"2021-07-22","cited_by_count":30},{"id":"1909.09712","title":"Learning an Adaptive Learning Rate Schedule","created":"2019-09-20","cited_by_count":29},{"id":"1802.08842","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","created":"2018-02-24","cited_by_count":28},{"id":"1810.05281","title":"IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics","created":"2018-10-11","cited_by_count":28},{"id":"2105.08541","title":"DACBench: A Benchmark Library for Dynamic Algorithm Configuration","created":"2021-05-18","cited_by_count":28},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28},{"id":"2106.05110","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","created":"2021-06-09","cited_by_count":25},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"2006.08246","title":"Learning Heuristic Selection with Dynamic Algorithm Configuration","created":"2020-06-15","cited_by_count":21},{"id":"1705.11159","title":"Reinforcement Learning for Learning Rate Control","created":"2017-05-31","cited_by_count":16},{"id":"1904.07801","title":"Online Selection of CMA-ES Variants","created":"2019-04-16","cited_by_count":11},{"id":"2202.03259","title":"Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration","created":"2022-02-07","cited_by_count":11},{"id":"1804.05650","title":"Theory of Parameter Control for Discrete Black-Box Optimization: Provable Performance Gains Through Dynamic Parameter Choices","created":"2018-04-16","cited_by_count":9},{"id":"1401.1024","title":"Solver Scheduling via Answer Set Programming","created":"2014-01-06","cited_by_count":7},{"id":"1602.04062","title":"Using Deep Q-Learning to Control Optimization Hyperparameters","created":"2016-02-12","cited_by_count":4},{"id":"1911.12200","title":"Learning Neural Search Policies for Classical Planning","created":"2019-11-27","cited_by_count":4},{"id":"1904.06230","title":"On the Impact of the Cutoff Time on the Performance of Algorithm Configurators","created":"2019-04-12","cited_by_count":3},{"id":"1810.09923","title":"Learning Classical Planning Strategies with Policy Gradient","created":"2018-10-23","cited_by_count":2},{"id":"2007.03336","title":"Fast Perturbative Algorithm Configurators","created":"2020-07-07","cited_by_count":2},{"id":"1606.01467","title":"Deep Q-Networks for Accelerating the Training of Deep Neural Networks","created":"2016-06-05","cited_by_count":1}],"next_cursor":null}