Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities

Authors: Yunwen Lei, Ke Tang

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical results are reported to support our theoretical findings. ... 6 Simulations: In this section, we include some experimental results to validate these theoretical findings. We apply SGD (4.1) with a linear kernel Kx = x and the hinge loss ℓ(a, y) = max{0, 1 ya} to several binary classification datasets (ADULT, GISETTE, IJCNN, MUSHROOMS, PHISHING and SPLICE).
Researcher Affiliation Academia Yunwen Lei and Ke Tang Shenzhen Key Laboratory of Computational Intelligence, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China leiyw@sustc.edu.cn tangk3@sustc.edu.cn
Pseudocode No The paper describes algorithms and update rules in text (e.g., equation 2.2) but does not provide any explicitly labeled pseudocode blocks or algorithms.
Open Source Code No The paper does not provide any explicit statements or links indicating that source code for the described methodology is publicly available.
Open Datasets Yes We apply SGD (4.1)... to several binary classification datasets (ADULT, GISETTE, IJCNN, MUSHROOMS, PHISHING and SPLICE). All these datasets, described in Supplementary Material G, can be download from the LIBSVM website [8]. [8] C.-C. Chang and C.-J. Lin. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):27, 2011.
Dataset Splits No The paper mentions training on datasets and plotting "test errors," but it does not specify any dataset splits (e.g., percentages for training, validation, and test sets) or describe a cross-validation setup.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments (e.g., CPU/GPU models, memory specifications).
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch versions) used in the experiments.
Experiment Setup Yes We consider polynomially decaying step sizes of the form ηt = 5t θ with θ {0.25, 0.51, 0.75} (we consider θ = 0.51, instead of θ = 0.5, since the associated step size sequence is square-summable). We repeat experiments 12 times and report the average of results.