4 papers
Meta-Learning Adaptive Loss Functions
Christian Raymond, Qi Chen, Bing Xue +1
Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for l…
Meta-Learning Loss Functions for Deep Neural Networks
Christian Raymond
Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require tho…
Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning
Christian Raymond, Qi Chen, Bing Xue +1
In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained und…
Meta-Learning Neural Procedural Biases
Christian Raymond, Qi Chen, Bing Xue +1
The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-…