paper-with-me

홈 › Papers

Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels

2016-12-01 · NeurIPS 2016 12 · Ilya O. Tolstikhin, Bharath K. Sriperumbudur, Bernhard Schölkopf

Maximum Mean Discrepancy (MMD) is a distance on the space of probability measures which has found numerous applications in machine learning and nonparametric testing. This distance is based on the notion of embedding probabilities in a reproducing kernel Hilbert space. In this paper, we present the first known lower bounds for the estimation of MMD based on finite samples. Our lower bounds hold for any radial universal kernel on $\R^d$ and match the existing upper bounds up to constants that depend only on the properties of the kernel. Using these lower bounds, we establish the minimax rate optimality of the empirical estimator and its $U$-statistic variant, which are usually employed in applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Nonparametric Density Estimation under Adversarial Losses

2018-05-22 · NeurIPS 2018 12 · Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li 외

We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy…

Density Estimation

Domain-Shift Aware Neural Networks for Unbalance Characterization in Rotating Systems

2026-06-17 · Bernardo Feijó Junqueira, Claudio Kiyoshi Umezu, Bruno Bilhar Karaziack, Tomaz Junior 외 arxiv

This work investigates the application of a domain-shift aware neural network for regression tasks aimed at estimating unbalance masses in rotating shafts under varying operating conditions. Experimental data were collec…

Domain Adaptation

Keep it Tighter -- A Story on Analytical Mean Embeddings

2021-10-15 · Linda Chamakh, Zoltan Szabo

Kernel techniques are among the most popular and flexible approaches in data science allowing to represent probability measures without loss of information under mild conditions. The resulting mapping called mean embeddi…

Portfolio Optimization

Ensemble Transport Filter via Optimized Maximum Mean Discrepancy

2024-07-16 · Dengfei Zeng, Lijian Jiang

In this paper, we present a new ensemble-based filter method by reconstructing the analysis step of the particle filter through a transport map, which directly transports prior particles to posterior particles. The trans…

Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing

2026-03-17 · Saksham Jain, Alex Luedtke arxiv

Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose…