On the Limitations of First-Order Approximation in GAN Dynamics

Authors: Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

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

Reproducibility Variable Result LLM Response
Research Type Experimental We first show experimentally that standard gradient dynamics of the GMM-GAN often fail to converge due to mode collapse or oscillatory behavior. ... In contrast, we then show that GAN dynamics with an optimal discriminator do converge, both experimentally and provably. Section 5 is titled "Experiments".
Researcher Affiliation Academia Jerry Li 1 Aleksander M adry 1 John Peebles 1 Ludwig Schmidt 1 1MIT. Correspondence to: Jerry Li <jerryzli@mit.edu>.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper uses a synthetic model (GMM-GAN) and does not specify or provide access information for any publicly available or open dataset.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology).
Hardware Specification No The paper does not provide specific hardware details 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 We set µ = ( 0.5, 0.5) as in Figure 1. ... ran the first order dynamics for 3000 iterations, with constant stepsize 0.3. We then repeated this 120 times for each grid point...