Model Function Based Conditional Gradient Method with Armijo-like Line Search

Authors: Peter Ochs, Yura Malitsky

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our algorithm is shown to perform favorably on a sparse non-linear robust regression problem and we discuss the flexibility of the proposed framework in several matrix factorization formulations. [...] Figure 1 shows the data and the convergence of the objective value or the model improvement with respect to actual computation time.
Researcher Affiliation Academia 1University of G ottingen, G ottingen, Germany 2Saarland University, Saarbr ucken, Germany. Correspondence to: Peter Ochs <ochs@math.uni-sb.de>.
Pseudocode Yes Algorithm 1 (Model Based Conditional Gradient Method with Line Search). [...] Algorithm 2 (Armijo Line Search for Algorithm 1).
Open Source Code No The paper does not provide any links to open-source code or state that the code will be made publicly available.
Open Datasets No The data for the experiment is generated randomly with P = 100, M = 1000, µ = 80, a = 20, b = 5, and 80% of coefficients aj are randomly set to 0.
Dataset Splits No The paper mentions data generation but does not specify any training, validation, or test splits by percentages or counts.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments.
Software Dependencies No The paper mentions using
Experiment Setup Yes The data for the experiment is generated randomly with P = 100, M = 1000, µ = 80, a = 20, b = 5, and 80% of coefficients aj are randomly set to 0. [...] We solve the inner problem using the Primal Dual Hybrid Gradient Algorithm with preconditioning (Pock & Chambolle, 2011), which allows for step sizes that are automatically computed based on Ki. We use warm starting for all methods. Our algorithm FW-Comp Lin LS and Prox Linear LS solve the subproblem up to a certain accuracy and perform an Armijo-like line search in the direction of the approximate solution.