Accelerated Method for Stochastic Composition Optimization With Nonsmooth Regularization

Authors: Zhouyuan Huo, Bin Gu, Ji Liu, Heng Huang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results verify our theoretical analysis.
Researcher Affiliation Academia 1Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA 15261, USA 2Department of Computer Science, University of Rochester, Rochester, NY, 14627, USA
Pseudocode Yes Algorithm 3 VRSC-PG
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it explicitly state that the code is publicly available.
Open Datasets No The paper uses synthetic data generated through Gaussian distributions for portfolio management and generates a Markov decision process (MDP) for reinforcement learning, without providing concrete access information for a publicly available dataset.
Dataset Splits No The paper uses generated synthetic data but does not explicitly specify training, validation, or testing dataset splits, percentages, or sample counts.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) 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 In our experiment, we set λ = 10 3 and A = B = b1 = 5. We just select the values of A, B, b1 casually, it is probable that we can get better results as long as we tune them carefully. ... learning rate η is tuned from {1, 10 1, 10 2, 10 3, 10 4}. We keep the learning rate constant for com-SVR-ADMM and VRSC-PG in the optimization.