DeepAI AI Chat
Log In Sign Up

Learning an Explicit Hyperparameter Prediction Policy Conditioned on Tasks

by   Jun Shu, et al.

Meta learning has attracted much attention recently in machine learning community. Contrary to conventional machine learning aiming to learn inherent prediction rules to predict labels for new query data, meta learning aims to learn the learning methodology for machine learning from observed tasks, so as to generalize to new query tasks by leveraging the meta-learned learning methodology. In this study, we interpret such learning methodology as learning an explicit hyperparameter prediction policy shared by all training tasks. Specifically, this policy is represented as a parameterized function called meta-learner, mapping from a training/test task to its suitable hyperparameter setting, extracted from a pre-specified function set called meta learning machine. Such setting guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks, instead of only obtaining fixed hyperparameters by many current meta learning methods, with less adaptability to query task's variations. Such understanding of meta learning also makes it easily succeed from traditional learning theory for analyzing its generalization bounds with general losses/tasks/models. The theory naturally leads to some feasible controlling strategies for ameliorating the quality of the extracted meta-learner, verified to be able to finely ameliorate its generalization capability in some typical meta learning applications, including few-shot regression, few-shot classification and domain generalization.


Few-Shot Learning with a Strong Teacher

Few-shot learning (FSL) aims to train a strong classifier using limited ...

3D Meta-Segmentation Neural Network

Though deep learning methods have shown great success in 3D point cloud ...

Improve Noise Tolerance of Robust Loss via Noise-Awareness

Robust loss minimization is an important strategy for handling robust le...

Bilevel Programming for Hyperparameter Optimization and Meta-Learning

We introduce a framework based on bilevel programming that unifies gradi...

Improved Compositional Generalization by Generating Demonstrations for Meta-Learning

Meta-learning and few-shot prompting are viable methods to induce certai...

Meta-Learning Parameterized First-Order Optimizers using Differentiable Convex Optimization

Conventional optimization methods in machine learning and controls rely ...