Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization

11/12/2020
by   Michal Lisicki, et al.
0

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.

READ FULL TEXT
research
02/11/2022

Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems

Over the recent years, reinforcement learning (RL) has shown impressive ...
research
07/07/2020

Curriculum learning for multilevel budgeted combinatorial problems

Learning heuristics for combinatorial optimization problems through grap...
research
11/02/2018

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

Machine translation systems based on deep neural networks are expensive ...
research
09/22/2022

How Good Is Neural Combinatorial Optimization?

Traditional solvers for tackling combinatorial optimization (CO) problem...
research
12/20/2021

Learning for Robust Combinatorial Optimization: Algorithm and Application

Learning to optimize (L2O) has recently emerged as a promising approach ...
research
12/24/2022

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Reinforcement learning (RL) problems can be challenging without well-sha...
research
06/13/2019

Curriculum Learning for Cumulative Return Maximization

Curriculum learning has been successfully used in reinforcement learning...

Please sign up or login with your details

Forgot password? Click here to reset