On Dropout and Nuclear Norm Regularization

Authors: Poorya Mianjy, Raman Arora

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate our theoretical findings with empirical results.
Researcher Affiliation Academia 1Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes 1The code for the experiments can be found at: https://github.com/r3831/dln_dropout
Open Datasets No The training data {xi} is sampled from a standard Gaussian distribution which in particular ensures that C = I. The labels {yi} are generated as yi Nxi, where N Rdk+1 d0.
Dataset Splits No The paper does not explicitly state training/validation/test dataset splits. It mentions training data but not its partitioning.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch or TensorFlow with their versions).
Experiment Setup Yes At each step of the dropout training, we use a minibatch of size 1000 to train the network. The learning rate is tuned over the set {1, 0.1, 0.01}. All experiments are repeated 50 times, the curves correspond to the average of the runs, and the grey region shows the standard deviation.