Efficient Sampling from Time-Varying Log-Concave Distributions
Authors: Hariharan Narayanan, Alexer Rakhlin
JMLR 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We propose a computationally efficient random walk on a convex body which rapidly mixes with respect to a fixed log-concave distribution and closely tracks a time-varying log-concave distribution. We develop general theoretical guarantees on the required number of steps; this number can be calculated on the fly according to the distance from and the shape of the next distribution. We then illustrate the technique on several examples. |
| Researcher Affiliation | Academia | Hariharan Narayanan EMAIL Department of Statistics and Department of Mathematics University of Washington; Alexander Rakhlin EMAIL Department of Statistics University of Pennsylvania |
| Pseudocode | No | The paper describes the steps of the random walk in narrative text within Section 3 ('The Markov Chain') rather than presenting them in a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code for the described methodology, nor does it provide links to any code repositories. |
| Open Datasets | No | The paper focuses on theoretical methods for sampling from log-concave distributions and their applications. It does not conduct experiments on specific, named datasets, thus no information on dataset availability is provided. |
| Dataset Splits | No | The paper does not report on experiments using specific datasets; therefore, it does not provide any information regarding dataset splits for training, validation, or testing. |
| Hardware Specification | No | This paper is theoretical in nature, proposing an algorithm and providing proofs for its properties. It does not describe any computational experiments that would require specific hardware, thus no hardware specifications are mentioned. |
| Software Dependencies | No | This paper is theoretical and does not include details about software dependencies or specific version numbers for any libraries or tools, as it does not report on empirical implementations. |
| Experiment Setup | No | The paper provides theoretical analysis of a sampling algorithm and its applications, including conditions for step sizes and number of steps. It does not, however, detail any specific experimental setup, hyperparameters, or training configurations for an empirical evaluation. |