Globally Gated Deep Linear Networks

Authors: Qianyi Li, Haim Sompolinsky

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our theory accurately captures the behavior of finite width GGDLNs trained with gradient descent (GD) dynamics.
Researcher Affiliation Academia 1Biophysics Graduate Program, Harvard University 2Center for Brain Science, Harvard University 3Edmond and Lily Safra Center for Brain Sciences, Hebrew University
Pseudocode No The paper describes mathematical derivations and theoretical concepts but does not include any pseudocode or explicitly labeled algorithm blocks.
Open Source Code Yes Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] In supplementary material
Open Datasets Yes In Fig.3 , we show parameter regimes where the bias can increase (Fig.3 (a-c)) or decrease (Fig.3 (d-f)) with σ on MNIST dataset [19] (Appendix C.3 ).
Dataset Splits Yes Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix C
Hardware Specification Yes Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] See Appendix C
Software Dependencies Yes Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix C
Experiment Setup Yes Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix C