Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces
Authors: Mojmir Mutny, Andreas Krause
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the improved inference error due to specially defined designs and new confidence sets on the problems of learning differential equations, linear bandits, gradient maps estimation, and stability verification of non-linear systems. In Section 7 we detail several example applications. |
| Researcher Affiliation | Academia | Mojmír Mutný ETH Zürich mojmir.mutny@inf.ethz.ch Andreas Krause ETH Zürich krausea.ethz.ch |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. Algorithms are described in text. |
| Open Source Code | No | The paper states "Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes]" in the checklist, but no specific URL or explicit statement about code release for the methodology described in the paper is found within the main text or appendices. |
| Open Datasets | No | The paper does not specify the use of a publicly available or open dataset with concrete access information (e.g., URL, DOI, specific repository, or formal citation). It discusses applications like pharmacokinetics, linear bandits, and learning ODE solutions, which imply data generation or specific problem settings rather than using standard public datasets with access details. |
| Dataset Splits | No | The paper does not provide specific train/validation/test dataset splits. While it mentions concepts like "train," "validation," and "test" as JSON keys for the schema, it does not detail how data was split for its own experiments in the text. |
| Hardware Specification | No | The paper states, "Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A] It’s insignificant. I just used a personal machine." This is not a specific hardware specification. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers, such as programming languages, libraries, or solvers. |
| Experiment Setup | Yes | The paper states "Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes]". Section 7.2 mentions "finite difference designs {Φ(x hei)}, where h is the stepsize and ei are unit vectors." Appendices E and F are cited for "information about optimization and rationale in choosing the κ, and V0" for applications, indicating some experimental setup details are provided there. |