A Generic Approach for Accelerating Stochastic Zeroth-Order Convex Optimization
Authors: Xiaotian Yu, Irwin King, Michael R. Lyu, Tianbao Yang
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical studies in various settings demonstrate the effectiveness of the proposed acceleration approach. In this section, we conduct experiments on two real-world datasets in various settings to demonstrate the superior performance of the proposed acceleration approach in Algorithm 1. |
| Researcher Affiliation | Academia | 1Department of Computer Science and Engineering The Chinese University of Hong Kong, Shatin, N.T., Hong Kong 2Shenzhen Key Laboratory of Rich Media Big Data Analytics and Applications, Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen, China 3Department of Computer Science, The University of Iowa, Iowa City, IA 52242, USA {xtyu,king,lyu}@cse.cuhk.edu.hk, tianbao-yang@uiowa.edu |
| Pseudocode | Yes | Algorithm 1 A generic approach for accelerating SZCO |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., a link or explicit statement) for the source code. |
| Open Datasets | Yes | We consider the ensemble learning setting of recommendations as a black-box optimization problem discussed in [Lian et al., 2016]. In particular, we blend the existing models in [Chen et al., 2011] for music recommendation competition in KDD-Cup 2011. We also consider an absolute loss and a huber loss [Zadorozhnyi et al., 2016] as objective functions. For better demonstrations of convergence rate, we sample 10 models from 237 models with predicted ratings denoted by w R10 in ensemble learning, and set the number of training points as N = 105. We consider industrial data on crystallization of ceramic thin films in [Nakamura et al., 2017]. |
| Dataset Splits | No | The paper mentions using "training points" but does not provide specific details on training, validation, or test dataset splits (e.g., percentages, absolute counts, or predefined splits). |
| Hardware Specification | Yes | We run experiments in a personal computer with Intel CPU@3.70GHz and 16GB memory. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The paper describes how parameters like step size (ηk) and smoothing parameter (δk) are set using formulas (e.g., "setting t = O(d2/ϵ2(2 θ)), δk = ϵk/(6G), ηk = ϵ3 k/(54G2d2B2)"). However, it does not provide concrete numerical values for these hyperparameters as used in the actual experiments depicted in the figures. |