推荐kotach · 2016-03
“Checkout Dagger [2], SEARN [3] and LOLS [1] (LOLS is available in vowpal wabbit search capabilities).”
推荐 Dagger、SEARN 和 LOLS,LOLS 已在 vowpal wabbit 中可用
LOLS:参考策略很差时也能改进的结构化预测搜索学习算法
结构化预测中的「学习搜索」方法通常模仿参考策略,已有理论只保证相对参考策略的遗憾较低,而当参考策略并不理想时这并不令人满意。作者提出新算法 LOLS,既相对参考策略表现良好,又保证相对于学得策略的偏离也有低遗憾(一种局部最优保证),因此能超越参考策略。在此基础上,作者还提出了结构化上下文赌博机这一部分信息的结构化预测设置。
评论者在讨论联合学习与结构化预测时推荐 LOLS,称其优于 Dagger、SEARN 等前作,并指出它已实现在 Vowpal Wabbit 的搜索功能中。
“Checkout Dagger [2], SEARN [3] and LOLS [1] (LOLS is available in vowpal wabbit search capabilities).”
“LOLS is a much superior method.”
“paper above also has a very good analysis on how to remove the search component of the inference and allow linear time complexity with competitive results.”
“Reinforcement learning can be used in the setting of joint learning because you play out the whole game before you do the learning.”