Generalized Eigenvalue Problems with Generative Priors

Authors: Zhaoqiang Liu, Wen Li, Junren Chen

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical results are provided to demonstrate the effectiveness of the proposed method.
Researcher Affiliation Academia Zhaoqiang Liu Wen Li University of Electronic Science and Technology of China {zqliu12, liwenbnu}@gmail.com Junren Chen University of Hong Kong chenjr58@connect.hku.hk
Pseudocode Yes Algorithm 1 Projected Rayleigh Flow Method (PRFM)
Open Source Code No The code will be open sourced after acceptance.
Open Datasets Yes In this section, we conduct proof-of-concept numerical experiments on the MNIST dataset [47]... Additional results for MNIST and Celeb A [55] are provided in Appendices D and E.
Dataset Splits No The paper mentions training on the 'original MNIST training set' and evaluating on a 'testing set', but it does not explicitly specify a validation split percentage or count.
Hardware Specification Yes All experiments are carried out using Python 3.10.6 and Py Torch 2.0.0, with an NVIDIA RTX 3060 Laptop 6GB GPU.
Software Dependencies Yes All experiments are carried out using Python 3.10.6 and Py Torch 2.0.0, with an NVIDIA RTX 3060 Laptop 6GB GPU.
Experiment Setup Yes The VAE is trained using the Adam optimizer with a mini-batch size of 100 and a learning rate of 0.001 on the original MNIST training set. To approximately perform the projection step PG( ), we use a gradient descent method with the Adam optimizer, with a step size of 100 and a learning rate of 0.1.