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 1310.4227cs.LGmath.PR
收藏

随机最大后验扰动的测度集中

On Measure Concentration of Random Maximum A-Posteriori Perturbations

Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);University of Haifa(海法大学);Massachusetts Institute of Technology(麻省理工学院)

Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi Jaakkola

摘要:

最大后验(MAP)扰动框架已成为一个有用的方法,在高维复杂模型的推理和学习。通过最大化随机扰动的势函数,MAP扰动从吉布斯分布生成无偏样本。不幸的是,生成如此多的高维随机变量的计算成本可能是令人望而却步的。更有效的算法使用基于低维MAP扰动的期望值的顺序采样策略。本文开发了新的测量浓度不等式,约束估计这些期望值所需的样本数。将一般结果应用于MAP扰动可以产生更有效的算法来近似Gibbs分布的采样。计量集中度结果具有普遍意义,并可能适用于涉及预期估计的其他领域。

英文摘要:

The maximum a-posteriori (MAP) perturbation framework has emerged as a useful approach for inference and learning in high dimensional complex models. By maximizing a randomly perturbed potential function, MAP perturbations generate unbiased samples from the Gibbs distribution. Unfortunately, the computational cost of generating so many high-dimensional random variables can be prohibitive. More efficient algorithms use sequential sampling strategies based on the expected value of low dimensional MAP perturbations. This paper develops new measure concentration inequalities that bound the number of samples needed to estimate such expected values. Applying the general result to MAP perturbations can yield a more efficient algorithm to approximate sampling from the Gibbs distribution. The measure concentration result is of general interest and may be applicable to other areas involving expected estimations.

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。

↑