Hyperparameter Optimization with Factorized Multilayer Perceptrons
نویسندگان
چکیده
In machine learning, hyperparameter optimization is a challenging task that is usually approached by experienced practitioners or in a computationally expensive brute-force manner such as grid-search. Therefore, recent research proposes to use observed hyperparameter performance on already solved problems (i.e. data sets) in order to speed up the search for promising hyperparameter configurations in the sequential model based optimization framework. In this paper, we propose multilayer perceptrons as surrogate models as they are able to model highly nonlinear hyperparameter response surfaces. However, since interactions of hyperparameters, data sets and metafeatures are only implicitly learned in the subsequent layers, we improve the performance of multilayer perceptrons by means of an explicit factorization of the interaction weights and call the resulting model a factorized multilayer perceptron. Additionally, we evaluate different ways of obtaining predictive uncertainty, which is a key ingredient for a decent tradeoff between exploration and exploitation. Our experimental results on two public meta data sets demonstrate the efficiency of our approach compared to a variety of published baselines. For reproduction purposes, we make our data sets and all the program code publicly available on our supplementary webpage.
منابع مشابه
Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks
In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of multilayer perceptrons; a parallel approach to optimize the architecture and initial weights of multilayer perceptrons; a method that searches for the parameters of the training algorithm, and an approach for cooperative co-evolut...
متن کاملComparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters
In this paper, we present a comparative study of several methods that combine evolutionary algorithms and local search methods to optimize multilayer perceptrons: A method that optimizes the architecture and initial weights of multilayer perceptrons; another that searches for training algorithm parameters, and finally, a co-evolutionary algorithm, introduced in this paper, that handles the arch...
متن کاملParallel Multiobjective Optimization of Ensembles of Multilayer Perceptrons for pattern classification
Pattern classification seeks to minimize error of unknown patterns, however, in many real world applications, type I (false positive) and type II (false negative) errors have to be dealt with separately, which is a complex problem since an attempt to minimize one of them usually makes the other grow. Actually, a type of error can be more important than the other, and a trade-off that minimizes ...
متن کاملAre Rosenblatt multilayer perceptrons more powerfull than sigmoidal multilayer perceptrons? From a counter example to a general result
In the eighties the problem of the lack of an efficient algorithm to train multilayer Rosenblatt perceptrons was solved by sigmoidal neural networks and backpropagation. But should we still try to find an efficient algorithm to train multilayer hardlimit neuronal networks, a task known as a NP-Complete problem? In this work we show that this would not be a waste of time by means of a counter ex...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015