Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always

Authors: Yi Feng, Ioannis Panageas, Xiao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments", "The experiments are designed to understand the behavior of A-MWU compared to classic MWU and Accelerated Mirror Descent (A-MD)...", "The experimental results indicate the following: As expected, all experiments have verified that A-MWU has a better convergence behavior and efficiency in escaping saddle points compared to classic MWU.
Researcher Affiliation Academia 1Shanghai University of Finance and Economics 2University of California, Irvine
Pseudocode Yes Algorithm 1 Single-Agent A-MWU
Open Source Code No No explicit statement about providing source code or a link to a code repository for the described methodology was found.
Open Datasets No The paper uses mathematical functions like 'Rosenbrock function', 'Bohachevsky function', 'Test function 1', and 'Test function 2' for experiments. These are not publicly available datasets in the form of files or repositories that can be accessed via a link or citation for reproducibility.
Dataset Splits No The paper does not provide specific details about training, validation, or test dataset splits. It mentions 'initial points' for the functions used in experiments but no data partitioning.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) used for running the experiments were provided in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions) were mentioned in the paper.
Experiment Setup Yes Parameter setting. In our experiments, we set the parameters as follows: β = 0.001 and µ = 1 for Rosenbrock function, Figure 1. β = 0.1 and µ = 1 for Bohachevsky function, Figure 2. β = 0.1 and µ = 0.2 for Test function 1, Figure 3. β = 0.001 and µ = 0.001 for Test function 2, Figure 4. β = 0.1 and µ = 0.5 for two-agent, Figure 5. ... and the step sizes are 0.01 for A-MWU, MWU and A-MD, see Figure 1.