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.
Conditional Sampling via Wasserstein Autoencoders and Triangular Transport
Department of Aeronautics & Astronautics, University of Washington, Seattle(华盛顿大学西雅图分校航空与航天系);Department of Applied Mathematics, University of Washington, Seattle(华盛顿大学西雅图分校应用数学系);Department of Mathematics, University of Washington, Seattle(华盛顿大学西雅图分校数学系)
Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps
CalTech(加州理工学院);Center for Data Science, New York University(纽约大学数据科学中心);Massachusets Institute of Technology(麻省理工学院);Courant Institute of Mathematical Sciences, New York University(纽约大学柯朗数学科学研究所)
Optimal Transport for Conditional Domain Matching and Label Shift
Criteo AI Lab(Criteo人工智能实验室);Ecole Polytechnique(巴黎综合理工学院);INSA de Rouen Normandie(鲁昂国立应用科学学院);Université Technologique de Compiègne(贡比涅技术大学);Université de Rouen Normandie(鲁昂诺曼底大学);Université de Bretagne Sud(南布列塔尼大学)
A generative flow for conditional sampling via optimal transport
University of the Philippines Diliman(菲律宾大学迪里曼分校);California Institute of Technology(加州理工学院);Columbia University(哥伦比亚大学);Baruch College(巴鲁克学院);University of Edinburgh(爱丁堡大学);Georgia Institute of Technology(佐治亚理工学院);Grinnell College(格林内尔学院);University of Michigan(密歇根大学);Yale University(耶鲁大学)
Department of Management, Economics and Industrial Engineering, Politecnico di Milano(米兰理工大学管理、经济与工业工程系);RFF-CMCC European Institute on Economics and the Environment (EIEE)(RFF-CMCC欧洲经济与环境研究所);Euro-Mediterranean Center on Climate Change (CMCC)(欧洲-地中海气候变化中心);Bocconi University, Department of Decision Sciences(博科尼大学决策科学系);MIT, Department of Nuclear Science and Engineering(麻省理工学院核科学与工程系)
Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference
SIAM Journal on Scientific Computing(SIAM科学计算杂志);Office of Naval Research(海军办公室);US Department of Energy, Office of Advanced Scientific Computing Research(美国能源部高级科学计算研究办公室);M2dt MMICC center(M2dt MMICC中心);Office of Advanced Scientific Computing Research(高级科学计算研究办公室);Air Force Office of Scientific Research(空军科学办公室);Department of Defense Vannevar Bush Faculty Fellowship(国防部门范纳瓦尔·布什教职员工 fellowship)
Neural Optimal Transport Meets Multivariate Conformal Prediction
Department of ML, MBZUAI(机器学习系,MBZUAI);MBZUAI, UAE(MBZUAI,阿联酋);CMAP, École polytechnique(CMAP,巴黎高等理工学院);Ecole Polytechnique, Palaiseau, France(巴黎高等理工学院,Palaiseau,法国)
CGAN-EB: A Non-parametric Empirical Bayes Method for Crash Hotspot Identification Using Conditional Generative Adversarial Networks: A Simulated Crash Data Study
CGAN-EB: A Non-parametric Empirical Bayes Method for Crash Hotspot Identification Using Conditional Generative Adversarial Networks: A Real-world Crash Data Study
From Conditional to Unconditional Independence: Testing Conditional Independence via Transport Maps
Institute of Statistics and Big Data, Renmin University of China(中国人民大学统计与大数据研究院);Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University(香港理工大学数据科学与人工智能学院);Department of Applied Mathematics, The Hong Kong Polytechnic University(香港理工大学应用数学系)
Nanjing University of Science and Technology(南京理工大学);PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education(PCA实验室,教育部高维信息智能感知与系统重点实验室);School of Computer Science and Engineering(计算机科学与工程学院)
Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Weierstrass Institute for Applied Analysis and Stochastics(魏尔斯特拉斯应用分析与随机过程研究所);Eidgenössische Technische Hochschule Zürich(苏黎世联邦理工学院)
SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Life Science and Technology, China Pharmaceutical University(中国药科大学生命科学与技术学院);Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen(深圳先进技术大学计算机科学与控制工程学院)
Conditional COT-GAN for Video Prediction with Kernel Smoothing
London School of Economics(伦敦政治经济学院);ETH Zurich(苏黎世联邦理工学院)
因果最优运输(COT)是在经典的最优运输问题上施加时间因果约束的结果,它自然地产生了一个新的概念,即路径空间上分布之间的距离。Xu等人(2020)首次将COT理论应用于顺序学习,其中COT-GAN被引入作为对抗算法,用于训练优化的隐式生成模型以产生顺序数据。依靠(Xu et al.,2020年),本文的贡献是双重的。首先,我们开发了一个适合序列预测的COT-GAN的条件版本。这意味着现在使用数据集来了解序列在观察其过去演变的情况下将如何演变。其次,我们通过核平滑修改经验测量来改进收敛结果(Pflug and Pichler(2016))。所得到的内核条件COT-GAN算法与视频预测的应用程序进行说明。
Fairness via Independence: A (Conditional) Distance Covariance Framework
School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, Hubei, China(华中科技大学数学与统计学院);Institute of Interdisciplinary Research for Mathematics and Applied Science & Hubei Key Laboratory of Engineering Modeling and Scientific Computing, Huazhong University of Science and Technology, Wuhan, Hubei, China(华中科技大学数学与应用科学交叉研究 institute 及湖北省工程建模与科学计算重点实验室)
Learning non-Gaussian graphical models via Hessian scores and triangular transport
Massachusetts Institute of Technology(麻省理工学院);University of Colorado Boulder(科罗拉多大学博尔德分校);Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔理工学院)