arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.08508stat.MLcs.LG
收藏

泛化与平坦极小值之间的PAC-贝叶斯联系

A PAC-Bayesian Link Between Generalisation and Flat Minima

Inria(法国国家信息与自动化研究所);PSL Research University(巴黎文理研究大学);Univ. Rennes(雷恩大学);CNRS(法国国家科学研究中心);IRISA(雷恩信息与自动化研究所);University College London(伦敦大学学院)

Maxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj

AI总结:

针对过参数化机器学习模型泛化能力的开放问题,该研究结合PAC-Bayes工具箱与庞加莱、对数索伯列夫不等式,提出含梯度项的新型泛化界,揭示平坦极小值对泛化性能的积极影响。

摘要:

现代机器学习通常涉及过参数化设置中的预测器(训练参数数量大于数据集大小),其训练不仅在训练数据上表现良好,还具有良好的泛化能力。这一现象挑战了许多理论结果,仍是一个开放问题。为了更好地理解,我们提供了涉及梯度项的新型泛化界。为此,我们将PAC-Bayes工具箱与庞加莱不等式和对数索伯列夫不等式相结合,避免了对预测器空间维度的显式依赖。我们的结果强调了平坦极小值(即其邻域也几乎最小化学习问题的极小值)对泛化性能的积极影响,直接体现了优化阶段的益处。

英文摘要:

Modern machine learning usually involves predictors in the overparameterised setting (number of trained parameters greater than dataset size), and their training yields not only good performance on training data, but also good generalisation capacity. This phenomenon challenges many theoretical results, and remains an open problem. To reach a better understanding, we provide novel generalisation bounds involving gradient terms. To do so, we combine the PAC-Bayes toolbox with Poincaré and Log-Sobolev inequalities, avoiding an explicit dependency on the dimension of the predictor space. Our results highlight the positive influence of flat minima (being minima with a neighbourhood nearly minimising the learning problem as well) on generalisation performance, involving directly the benefits of the optimisation phase.

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。

↑