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 2305.15901cs.LG
收藏

使用经验条件测度的一致最优传输

Consistent Optimal Transport with Empirical Conditional Measures

IIT Hyderabad(印度理工学院海得拉巴分校);Microsoft(微软公司);Amazon(亚马逊公司)

Piyushi Manupriya, Rachit Keerti Das, Sayantan Biswas, Saketha Nath Jagarlapudi

AI总结:

针对连续且边缘分布不同的共同条件变量,本文提出用核化最小二乘项隐式匹配经验条件分布的一致 OT 估计方法,并给出渐近最优性、有限样本界及应用提升。

摘要:

给定来自两个联合分布的样本,我们研究在以一个共同变量为条件时二者之间的最优传输(Optimal Transportation,OT)问题。我们关注条件变量可能连续、且该变量在两个联合分布中的边缘分布可能不同的一般情形。在此类设置中,标准 OT 变体无法使用,因此需要新的估计技术。由于主要挑战在于条件分布并非显式可得,我们 OT 公式化中的关键思想是采用在联合样本上计算的核化最小二乘项,这些项隐式地使传输计划的边缘分布与经验条件分布相匹配。在温和条件下,我们证明所估计的传输计划作为条件变量的函数具有渐近最优性。对于有限样本,我们表明其在正则化目标意义下的偏差以 $O(1/m^{1/4})$ 为界,其中 $m$ 为样本数量。我们还讨论了如何使用显式概率模型以及隐式生成模型来建模条件传输计划。我们在最优计划可解析得知的合成数据集上实证验证了估计量的一致性。当应用于少样本分类的提示学习以及预测细胞对治疗反应情境下的条件生成等任务时,我们的方法相较最先进方法取得了改进。

英文摘要:

Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between them when conditioned on a common variable. We focus on the general setting where the conditioned variable may be continuous, and the marginals of this variable in the two joint distributions may not be the same. In such settings, standard OT variants cannot be employed, and novel estimation techniques are necessary. Since the main challenge is that the conditional distributions are not explicitly available, the key idea in our OT formulation is to employ kernelized-least-squares terms computed over the joint samples, which implicitly match the transport plan's marginals with the empirical conditionals. Under mild conditions, we prove that our estimated transport plans, as a function of the conditioned variable, are asymptotically optimal. For finite samples, we show that the deviation in terms of our regularized objective is bounded by $O(1/m^{1/4})$, where $m$ is the number of samples. We also discuss how the conditional transport plan could be modelled using explicit probabilistic models as well as using implicit generative ones. We empirically verify the consistency of our estimator on synthetic datasets, where the optimal plan is analytically known. When employed in applications like prompt learning for few-shot classification and conditional-generation in the context of predicting cell responses to treatment, our methodology improves upon state-of-the-art methods.

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。

↑