-
Scaling Imitation Learning in Minecraft
Imitation learning is a powerful family of techniques for learning senso...
read it
-
Sherpa: Robust Hyperparameter Optimization for Machine Learning
Sherpa is a hyperparameter optimization library for machine learning mod...
read it
-
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
StarCraft, one of the most difficult esport games with long-standing his...
read it
-
DERAIL: Diagnostic Environments for Reward And Imitation Learning
The objective of many real-world tasks is complex and difficult to proce...
read it
-
On the Decision Boundary of Deep Neural Networks
While deep learning models and techniques have achieved great empirical ...
read it
-
Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
Deep learning techniques have become the method of choice for researcher...
read it
Training Stronger Baselines for Learning to Optimize
Learning to optimize (L2O) has gained increasing attention since classical optimizers require laborious problem-specific design and hyperparameter tuning. However, there is a gap between the practical demand and the achievable performance of existing L2O models. Specifically, those learned optimizers are applicable to only a limited class of problems, and often exhibit instability. With many efforts devoted to designing more sophisticated L2O models, we argue for another orthogonal, under-explored theme: the training techniques for those L2O models. We show that even the simplest L2O model could have been trained much better. We first present a progressive training scheme to gradually increase the optimizer unroll length, to mitigate a well-known L2O dilemma of truncation bias (shorter unrolling) versus gradient explosion (longer unrolling). We further leverage off-policy imitation learning to guide the L2O learning, by taking reference to the behavior of analytical optimizers. Our improved training techniques are plugged into a variety of state-of-the-art L2O models, and immediately boost their performance, without making any change to their model structures. Especially, by our proposed techniques, an earliest and simplest L2O model can be trained to outperform the latest complicated L2O models on a number of tasks. Our results demonstrate a greater potential of L2O yet to be unleashed, and urge to rethink the recent progress. Our codes are publicly available at: https://github.com/VITA-Group/L2O-Training-Techniques.
READ FULL TEXT
Comments
There are no comments yet.