Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates

Authors: Zhuanghua Liu, Luo Luo, Bryan Kian Hsiang Low

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The numerical experiments show the proposed methods significantly outperform the baseline methods. ... We compare the proposed methods LISR-1 and LISR-k with baseline methods including IQN (Mokhtari, Eisen, and Ribeiro 2018) and SLIQN (Lahoti et al. 2023). We test all methods on the problems of quadratic programming and regularized logistic regression.
Researcher Affiliation Collaboration Zhuanghua Liu1, 2, Luo Luo*3, Bryan Kian Hsiang Low1 1Department of Computer Science, National University of Singapore 2CNRS@CREATE LTD, 1 Create Way, #08-01 CREATE Tower, Singapore 138602 3School of Data Science, Fudan University
Pseudocode Yes Algorithm 1: LISR-1
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the methodology described.
Open Datasets Yes We conduct our experiments on nine real-world datasets ( a9a , w8a , ijcnn , mushrooms , phishing , svmguide3 , german.numer , splice and covtype ) from LIBSVM repository.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology).
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes For the LISR-k method, we set k = 5 for all of the cases. For the fairness of comparison, we run all algorithms from the same initial point. ... We run the experiments by taking n = 1000, d = 50 and ξ {4, 8, 12}... We take λ = 10 3 for a9a , mushrooms , svmguide3 , german.numer , covtype and λ = 10 4 for others.