Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time

Authors: Burak Bartan, Mert Pilanci

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the method s performance on synthetic and real datasets.
Researcher Affiliation Academia 1Department of Electrical Engineering, Stanford University, CA, USA.
Pseudocode Yes Algorithm 1 Binary NFDA for Re LU activation
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes We have tested the performance of the binary NFDA method on the two spirals dataset (Chalup & Wiklendt, 2007)
Dataset Splits No The paper mentions using training samples for the MNIST dataset ('n = 60000 training samples of the MNIST dataset') but does not specify explicit training, validation, or test splits, nor does it mention cross-validation or predefined splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions using 'Python' and 'CVXPY (Diamond & Boyd, 2016)' but does not specify version numbers for these software components.
Experiment Setup Yes For the NFDA method, we have used P = 100 unique Dj matrices.