An LP-based hyperparameter optimization model for language modeling

Amir Hossein Akhavan Rahnama, Mehdi Toloo*, Nezer Jacob Zaidenberg

*المؤلف المقابل لهذا العمل

نتاج البحث: المساهمة في مجلةArticleمراجعة النظراء

3 اقتباسات (Scopus)


In order to find hyperparameters for a machine learning model, algorithms such as grid search or random search are used over the space of possible values of the models’ hyperparameters. These search algorithms opt the solution that minimizes a specific cost function. In language models, perplexity is one of the most popular cost functions. In this study, we propose a fractional nonlinear programming model that finds the optimal perplexity value. The special structure of the model allows us to approximate it by a linear programming model that can be solved using the well-known simplex algorithm. To the best of our knowledge, this is the first attempt to use optimization techniques to find perplexity values in the language modeling literature. We apply our model to find hyperparameters of a language model and compare it to the grid search algorithm. Furthermore, we illustrate that it results in lower perplexity values. We perform this experiment on a real-world dataset from SwiftKey to validate our proposed approach.

اللغة الأصليةEnglish
الصفحات (من إلى)2151-2160
عدد الصفحات10
دوريةJournal of Supercomputing
مستوى الصوت74
رقم الإصدار5
المعرِّفات الرقمية للأشياء
حالة النشرPublished - مايو 1 2018

ASJC Scopus subject areas

  • ???subjectarea.asjc.1700.1712???
  • ???subjectarea.asjc.2600.2614???
  • ???subjectarea.asjc.1700.1710???
  • ???subjectarea.asjc.1700.1708???

قم بذكر هذا