Exact Optimal Accelerated Complexity for Fixed-Point Iterations

Authors: Jisun Park, Ernest K Ryu

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we provide experiments with CT imaging, optimal transport, and decentralized optimization to demonstrate the practical effectiveness of the acceleration mechanism.
Researcher Affiliation Academia 1Department of Mathematical Sciences, Seoul National University.
Pseudocode No The paper describes algorithms using mathematical equations and definitions but does not include 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 mentions using a "Modified Shepp-Logan phantom image" and defines probability distributions/sparse signals within the text or figures, but it does not provide concrete access information (e.g., links, DOIs, formal citations) for a publicly available dataset.
Dataset Splits No The paper does not describe specific train/validation/test dataset splits. The experiments are demonstrations or simulations rather than typical machine learning experiments with data partitioning.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes In Section 6.2 (CT imaging), parameters are given as "α = 0.01, β = 0.03 and λ = 1.0". In Section 6.3 (Earth mover's distance), parameters are "µ = 1.0 × 10−6 and ε = 1.0". In Section 6.4 (Decentralized optimization), "stepsize α = 0.005 and regularization parameter λ = 0.002 for 100 iterations" are specified.