arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.04460cs.LGmath.STstat.MLstat.TH
收藏

仍然没有免费的午餐:为更严格的PAC-Bayes边界付出的代价

Still no free lunches: the price to pay for tighter PAC-Bayes bounds

Inria(法国国家信息与自动化研究所);University College London(伦敦大学学院);Université Paris-Saclay(巴黎萨克雷大学)

Benjamin Guedj, Louis Pujol

摘要:

“没有免费的午餐”结果表明,在没有事先假设和建模的情况下,不可能获得学习算法误差的有意义的范围。有些模型是昂贵的(强假设,如亚高斯尾),其他的是便宜的(简单的有限方差)。众所周知,你付出的越多,你得到的就越多:换句话说,最昂贵的模型产生的边界更有趣。鲁棒统计学的最新进展研究了在保持成本最小的同时获得紧界的过程。本论文探讨和展览的限制是什么,以获得紧凑的PAC-贝叶斯界在一个强大的设置便宜的模型,解决的问题:PAC-贝叶斯好钱的价值?

英文摘要:

"No free lunch" results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling. Some models are expensive (strong assumptions, such as as subgaussian tails), others are cheap (simply finite variance). As it is well known, the more you pay, the more you get: in other words, the most expensive models yield the more interesting bounds. Recent advances in robust statistics have investigated procedures to obtain tight bounds while keeping the cost minimal. The present paper explores and exhibits what the limits are for obtaining tight PAC-Bayes bounds in a robust setting for cheap models, addressing the question: is PAC-Bayes good value for money?

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑