Non-stochastic Best Arm Identification and Hyperparameter Optimization

Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best-arm identification framework has only been considered in the stochastic setting. We introduce the non-stochastic setting under this framework, identify a known algorithm that is well-suited for this setting, and analyze its behavior. Next, by leveraging the iterative nature of standard machine learning algorithms, we cast hyperparameter optimization as an instance of non-stochastic best-arm identification, and empirically evaluate our proposed algorithm on this task. Our empirical results show that, by allocating more resources to promising hyperparameter settings, we typically achieve comparable test accuracies an order of magnitude faster than baseline methods.

[1]  Peter Auer,et al.  The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[2]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[3]  Stephen F. Smith,et al.  The Max K-Armed Bandit: A New Model of Exploration Applied to Search Heuristic Selection , 2005, AAAI.

[4]  Shie Mannor,et al.  Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems , 2006, J. Mach. Learn. Res..

[5]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[6]  Rémi Munos,et al.  Pure Exploration in Multi-armed Bandits Problems , 2009, ALT.

[7]  Dominik D. Freydenberger,et al.  Can We Learn to Gamble Efficiently? , 2010, COLT.

[8]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[11]  Kevin Leyton-Brown,et al.  Sequential Model-Based Optimization for General Algorithm Configuration , 2011, LION.

[12]  András György,et al.  Efficient Multi-Start Strategies for Local Search Algorithms , 2009, J. Artif. Intell. Res..

[13]  Aurélien Garivier,et al.  The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond , 2011, COLT.

[14]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[15]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[16]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[17]  Peter L. Bartlett,et al.  Oracle inequalities for computationally adaptive model selection , 2012, ArXiv.

[18]  Sébastien Bubeck,et al.  Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems , 2012, Found. Trends Mach. Learn..

[19]  Ambuj Tewari,et al.  PAC Subset Selection in Stochastic Multi-armed Bandits , 2012, ICML.

[20]  Alessandro Lazaric,et al.  Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence , 2012, NIPS.

[21]  Tim Kraska,et al.  MLbase: A Distributed Machine-learning System , 2013, CIDR.

[22]  Oren Somekh,et al.  Almost Optimal Exploration in Multi-Armed Bandits , 2013, ICML.

[23]  Christopher Ré,et al.  Parallel stochastic gradient algorithms for large-scale matrix completion , 2013, Mathematical Programming Computation.

[24]  Jasper Snoek,et al.  Input Warping for Bayesian Optimization of Non-Stationary Functions , 2014, ICML.

[25]  Jasper Snoek,et al.  Freeze-Thaw Bayesian Optimization , 2014, ArXiv.

[26]  Matthew Malloy,et al.  lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits , 2013, COLT.

[27]  Tim Kraska,et al.  TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries , 2015, ArXiv.

[28]  Ameet Talwalkar,et al.  MLlib: Machine Learning in Apache Spark , 2015, J. Mach. Learn. Res..

[29]  Aurélien Garivier,et al.  On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models , 2014, J. Mach. Learn. Res..