Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity

Authors: Sally Dong, Haotian Jiang, Yin Tat Lee, Swati Padmanabhan, Guanghao Ye

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Therefore, even though the focus of our work has been on developing the theory, the preceding discussion suggests that there could be an implementation of our algorithm which can perform reasonably well in practice. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Researcher Affiliation Academia Sally Dong Computer Science & Engineering University of Washington Seattle, WA 98195 sallyqd@uw.edu Haotian Jiang Computer Science & Engineering University of Washington Seattle, WA 98195 jhtdavid@uw.edu Yin Tat Lee Computer Science & Engineering University of Washington Seattle, WA 98195 yintat@uw.edu Swati Padmanabhan Electrical & Computer Engineering University of Washington Seattle, WA 98195 pswati@uw.edu Guanghao Ye Department of Mathematics Massachusetts Institute of Technology Cambridge, MA 02142 ghye@mit.edu
Pseudocode Yes Algorithm 1 Minimizing Decomposable Convex Function
Open Source Code No The paper focuses on theoretical development and does not mention providing open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not conduct experiments with datasets.
Dataset Splits No The paper is theoretical and does not report experiments requiring data splits.
Hardware Specification No The paper is theoretical and does not report experiments run on specific hardware, thus no hardware specifications are provided for its own work. While it mentions performance of related tools, it does not specify hardware for its own algorithm's evaluation.
Software Dependencies No The paper is theoretical and does not report experiments, so it does not list software dependencies with specific version numbers for its own implementation or evaluation.
Experiment Setup No The paper is theoretical and does not report experiments, thus no specific experimental setup details or hyperparameters are provided.