A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

Authors: Junhyung Park, Krikamol Muandet

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We derive a natural regression interpretation to obtain empirical estimates, and provide a thorough theoretical analysis thereof, including universal consistency. As natural by-products, we obtain the conditional analogues of the maximum mean discrepancy and Hilbert-Schmidt independence criterion, and demonstrate their behaviour via simulations.
Researcher Affiliation Academia Junhyung Park MPI for Intelligent Systems, Tübingen junhyung.park@tuebingen.mpg.de Krikamol Muandet MPI for Intelligent Systems, Tübingen krikamol@tuebingen.mpg.de
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper uses simulated data generated from specified distributions (e.g., Z N(0, 1), X = e 0.5Z2 sin(2Z) + NX), and does not provide access information for a publicly available or open dataset.
Dataset Splits No The paper simulates data but does not provide specific dataset split information (e.g., train/validation/test percentages or counts, or cross-validation setup) needed to reproduce data partitioning.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes In all simulations, we use the Gaussian kernel k X (x, x ) = k Y(x, x ) = k Z(x, x ) = e 1 2 σX x x 2 2 with hyperparameter σX = 0.1, and regularisation parameter λ = 0.01. with regularisation λn = 10 7n 1 4 .