Estimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM
We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on $n$ independent samples from them. Curiously, we show that estimating the IPM itself between probability measures, is not significantly easier than estimating the probability measures under the IPM. We prove that the minimax optimal rates for these two problems are multiplicatively equivalent, up to a $\log \log (n)/\log (n)$ factor.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Integral Imprecise Probability Metrics
Quantifying differences between probability distributions is fundamental to statistics and machine learning, primarily for comparing statistical uncertainty. In contrast, epistemic uncertainty (EU) -- due to incomplete k…
Uncertainty QuantificationRobust peak-to-peak gain analysis using integral quadratic constraints
This work provides a framework to compute an upper bound on the robust peak-to-peak gain of discrete-time uncertain linear systems using integral quadratic constraints (IQCs). Such bounds are of particular interest in th…
Covariate balancing using the integral probability metric for causal inference
Weighting methods in causal inference have been widely used to achieve a desirable level of covariate balancing. However, the existing weighting methods have desirable theoretical properties only when a certain model, ei…
Causal InferenceregressionSample Complexity Bounds for Estimating Probability Divergences under Invariances
Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributio…
Density EstimationIntegral Geometric Dual Distributions of Multilinear Models
We propose an integral geometric approach for computing dual distributions for the parameter distributions of multilinear models. The dual distributions can be computed from, for example, the parameter distributions of c…