Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with BM25 Similarity

Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with... AbstractIn machine learning, hyperparameter tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. Several approaches have been widely adopted for hyperparameter tuning, which is typically a time consuming process. We propose an efficient technique to speed up the process of hyperparameter tuning with Grid Search. We applied this technique on text categorization using kNN algorithm with BM25 similarity, where three hyperparameters need to be tuned. Our experiments show that our proposed technique is at least an order of magnitude faster than conventional tuning. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Open Computer Science de Gruyter

Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with BM25 Similarity

Ghawi, Raji; Pfeffer, Jürgen
Open Computer Science , Volume 9 (1): 21 – Jan 1, 2019
Download PDF
21 pages

Loading next page...
 
/lp/de-gruyter/efficient-hyperparameter-tuning-with-grid-search-for-text-czwO4Rqkhl
Publisher
de Gruyter
Copyright
© 2019 Raji Ghawi et al., published by De Gruyter Open
eISSN
2299-1093
DOI
10.1515/comp-2019-0011
Publisher site
See Article on Publisher Site

Abstract

AbstractIn machine learning, hyperparameter tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. Several approaches have been widely adopted for hyperparameter tuning, which is typically a time consuming process. We propose an efficient technique to speed up the process of hyperparameter tuning with Grid Search. We applied this technique on text categorization using kNN algorithm with BM25 similarity, where three hyperparameters need to be tuned. Our experiments show that our proposed technique is at least an order of magnitude faster than conventional tuning.

Journal

Open Computer Science – de Gruyter

Published: Jan 1, 2019

References

  • Classification Based on Multi - word with Support Vector Machine Know Based knosys
    Zhang
  • Using the K Nearest Neighbor Method and in the Patent Document Categorization Subtask at In Proceedings of the Fifth NTCIR Workshop Meeting on Evaluation of Information Access Technologies Question Answering and Cross - Lingual Information Access Japan
    Murata
  • Efficient Global Optimization of Expensive Black - Box Functions of Optimization
    Jones
  • de A Tutorial on Bayesian Optimization of Expensive Cost Functions with Application to Active User Modeling and Hierarchical Reinforcement Learning
    Brochu
  • Match KNN - based Approach for Large - scale Product Categorization in SIGIR Workshop on eCommerce eCom Data Challenge New York
    Hu
  • Sequential Model - Based Optimization for General Algorithm Configuration in ed Learning and Intelligent Optimization
    Hutter
  • Dom Using Taxonomy Discriminants and Signatures for Navigating in Text Databases In Proceedings of the rd on Large Publishers San Francisco CA
    Chakrabarti
  • Nearest Neighbour Algorithm for Large - scale Hierarchical Multi - label Classification In Proceedings of the Joint ECML PASCAL Workshop on Large Scale Hierarchical Classification volume Athens
    Wang
  • Design and regularization of neural networks : the optimal use of a validation set in for Processing VI Proceedings of the Processing Workshop
    Larsen
  • Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves In Proceedings of the th International Conference on Artificial
    Domhan
  • Hierarchically Classifying Documents Using Very Few Words In Proceedings of the Fourteenth International Conference on Machine Learning Kauf - mann Publishers San Francisco CA
    Koller
  • for Ranking Functions with Multiple Parameters In Proceedings of the th ACM International Conference on Information and Knowledge Management New York
    Taylor
  • for Hyper - parameter Optimization In Proceedings of the th International Conference on Neural Information Processing Systems NIPS Associates
    Bergstra
  • Expert Network : Effective and Efficient Learning from Human Decisions in Text Categorization and Retrieval in eds London
    Yang
  • Combined selection and hyperparameter optimization of classification algorithms In Proceedings of the th ACM SIGKDD international conference on Knowledge discovery and data mining
    Thornton
  • Joins that Generalize Classification Using WHIRL In Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining New York City New York
    Cohen
  • Neural Network Approach to Topic Spotting
    Wiener
  • Using kNN Model for Automatic Categorization
    Guo
  • Choosing Multiple Parameters for Support Vector Machines
    Chapelle
  • The Probabilistic Relevance Framework Beyond Foundations and Trends in
    Robertson
  • Random for - parameter Optimization of Learning
    Bergstra
  • Gradient - Based Optimization of
    Bengio
  • in
    Claesen
  • Practical Bayesian Optimization of Machine Learning In Proceedings of the th International Conference on Neural Information Processing Systems - Volume NIPS
    Snoek
  • Gradient - based hyper - parameter optimization through reversible learning in International Conference on Machine
    Maclaurin
  • Categorization Using Weight Adjusted k - Nearest Neighbor Classification In Proceedings of the th Pacific - Asia Conference on Knowledge Discovery and Data Mining
    Han
  • Do Efficient Multiple Hyperparameter Learning for Log - linear Models In Proceedings of the th International Conference on Neural Information Processing Systems NIPS Associates
    Curran
  • Naive at Forty : The Independence Assumption in In Proceedings of the th European Conference on
    Lewis
  • An Evaluation of Statistical Approaches to Categorization
    Yang
  • Bayesian Optimization in a Billion Dimensions via Random Embeddings of
    Wang
  • Practical Solutions to the Problem of Diagonal Dominance in Kernel Document Clustering In rd International Conference on Machine learning
    Greene
  • Heterogeneous uncertainty sampling for supervised learning in Proceedings
    Lewis
  • Hierarchical Deep Learning for Classification
    Kowsari
  • Nearest Neighbor Norms Pattern Classification Techniques Los CA
    Dasarathy
  • Joachims Categorization with Support Vector Machines : Learning with Many Relevant Features In Proceedings of the th European Conference on Machine Learning
    Springer
  • Term Frequency Normalisation Tuning for Models in eds in
    He
  • Automatic Processing The Transformation Retrieval of by Publishing Co
    Salton
  • Multi - Source Social Feedback of Online News Feeds
    Moniz