Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization
Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems. The field recently experienced growth by successfully adapting architectures originally designed for machine translation. Even though the results are promising, a large gap still exists between NCO models and classic deterministic solvers, both in terms of accuracy and efficiency. One of the drawbacks of current approaches is the inefficiency of training on multiple problem sizes. Curriculum learning strategies have been shown helpful in increasing performance in the multi-task setting. In this work, we focus on designing a curriculum learning-based training procedure that can help existing architectures achieve competitive performance on a large range of problem sizes simultaneously. We provide a systematic investigation of several training procedures and use the insights gained to motivate application of a psychologically-inspired approach to improve upon the classic curriculum method.
Code (0)
등록된 구현이 없습니다.
Tasks
Combinatorial OptimizationEfficient Neural NetworkMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization
Over the recent years, reinforcement learning (RL) starts to show promising results in tackling combinatorial optimization (CO) problems, in particular when coupled with curriculum learning to facilitate training. Despit…
Combinatorial OptimizationReinforcement Learning (RL)Curriculum learning for multilevel budgeted combinatorial problems
Learning heuristics for combinatorial optimization problems through graph neural networks have recently shown promising results on some classic NP-hard problems. These are single-level optimization problems with only one…
Combinatorial OptimizationMulti-agent Reinforcement LearningNonlinear Bayesian optimal experimental design using logarithmic Sobolev inequalities
We study the problem of selecting $k$ experiments from a larger candidate pool, where the goal is to maximize mutual information (MI) between the selected subset and the underlying parameters. Finding the exact solution …
Combinatorial OptimizationExperimental DesignUnderstanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics
Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting …
Compiling Combinatorial Prediction Games
In online optimization, the goal is to iteratively choose solutions from a decision space, so as to minimize the average cost over time. As long as this decision space is described by combinatorial constraints, the …
NegationPrediction