Continuous-time Models for Stochastic Optimization Algorithms

Authors: Antonio Orvieto, Aurelien Lucchi

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We verify this result on a one dimensional quadratic, under the choice of parameters in our example, using Euler-Maruyama simulation (i.e. PGD) with h = 10 3, σ = 5. In Fig. 1 we show the mean and standard deviation relative to 20 realization of the Gaussian noise.
Researcher Affiliation Academia Antonio Orvieto Department of Computer Science ETH Zurich, Switzerland Aurelien Lucchi Department of Computer Science ETH Zurich, Switzerland
Pseudocode No The paper presents mathematical equations and descriptions of algorithms (e.g., MB-PGD, VR-PGD) but does not include any formally labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets No The empirical verification is performed on 'a one dimensional quadratic', which is a synthetic function used for simulation and not a publicly available dataset with concrete access information.
Dataset Splits No The paper describes a simulation on a synthetic one-dimensional quadratic function and does not provide details about training, validation, or test dataset splits.
Hardware Specification No The paper mentions 'using Euler-Maruyama simulation' but does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running this simulation.
Software Dependencies No The paper mentions 'Euler-Maruyama simulation' as the method used, but does not provide specific software dependencies or version numbers (e.g., programming languages, libraries, or simulation software with versions) needed to replicate the experiment.
Experiment Setup Yes We verify this result on a one dimensional quadratic, under the choice of parameters in our example, using Euler-Maruyama simulation (i.e. PGD) with h = 10 3, σ = 5.