Multi-Task Multicriteria Hyperparameter Optimization
This work addresses hyperparameter optimization for researchers and practitioners dealing with multi-task and multi-criteria scenarios, but it appears incremental as it builds on existing Pareto-optimal and multi-task optimization concepts.
The authors tackled the problem of selecting optimal hyperparameters across multiple tasks and criteria by proposing the Multi-Task Multi Criteria (MTMC) method, which generates Pareto-optimal solutions and selects one based on given significance coefficients, as demonstrated in an image classification task using a convolutional neural network.
We present a new method for searching optimal hyperparameters among several tasks and several criteria. Multi-Task Multi Criteria method (MTMC) provides several Pareto-optimal solutions, among which one solution is selected with given criteria significance coefficients. The article begins with a mathematical formulation of the problem of choosing optimal hyperparameters. Then, the steps of the MTMC method that solves this problem are described. The proposed method is evaluated on the image classification problem using a convolutional neural network. The article presents optimal hyperparameters for various criteria significance coefficients.