883 citations · 2.5k across the 44 of their papers we have counts for
5 papers · 1 filter
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…
Genetic Programming for Manifold Learning: Preserving Local Topology
Andrew Lensen, Bing Xue, Mengjie Zhang
Manifold learning methods are an invaluable tool in today's world of increasingly huge datasets. Manifold learning algorithms can discover a much lower-dimensional representation (…
Improving generalisation of AutoML systems with dynamic fitness evaluations
Benjamin Patrick Evans, Bing Xue, Mengjie Zhang
A common problem machine learning developers are faced with is overfitting, that is, fitting a pipeline too closely to the training data that the performance degrades for unseen da…
Effective Exploration for Deep Reinforcement Learning via Bootstrapped Q-Ensembles under Tsallis Entropy Regularization
Gang Chen, Yiming Peng, Mengjie Zhang
Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effecti…
An Adaptive Clipping Approach for Proximal Policy Optimization
Gang Chen, Yiming Peng, Mengjie Zhang
Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by th…