Dropout as a Structured Shrinkage Prior

Authors: Eric Nalisnick, Jose Miguel Hernandez-Lobato, Padhraic Smyth

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

Reproducibility Variable Result LLM Response
Research Type Experimental We performed experiments to test the practicality of the tail-adaptive importance sampling scheme (Section 5.2) for MC dropout and the variational EM algorithm (Section 5.3) for ARD, ADD, and ARD-ADD priors (Section 4). For both cases we used the same experimental setup as Gal & Ghahramani (2016b), testing the models on regression tasks from the UCI repository (Dheeru & Karra Taniskidou, 2017). The supplementary materials include details of the model and optimization hyperparameters as well as Python implementations2 of both experiments.Table 2. Comparing Monte Carlo Objectives. We compare test set RMSE and test log-likelihood for UCI regression benchmarks.
Researcher Affiliation Collaboration Eric Nalisnick 1 José Miguel Hernández-Lobato 1 2 3 Padhraic Smyth 4 1Department of Engineering, University of Cambridge, Cambridge, United Kingdom 2Microsoft Research, Cambridge, United Kingdom 3Alan Turing Institute 4Department of Computer Science, University of California, Irvine, United States of America. Correspondence to: Eric Nalisnick <e.nalisnick@eng.cam.ac.uk>.
Pseudocode No No structured pseudocode or algorithm blocks, or clearly labeled algorithm sections, were found.
Open Source Code Yes The supplementary materials include details of the model and optimization hyperparameters as well as Python implementations2 of both experiments. 2Available at: https://github.com/enalisnick/dropout_icml2019
Open Datasets Yes For both cases we used the same experimental setup as Gal & Ghahramani (2016b), testing the models on regression tasks from the UCI repository (Dheeru & Karra Taniskidou, 2017).
Dataset Splits No The paper refers to using the same experimental setup as Gal & Ghahramani (2016b), but does not explicitly state specific train/validation/test split percentages, sample counts, or cross-validation details within its own text.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments were provided.
Software Dependencies No The paper mentions 'Python implementations' but does not provide specific version numbers for Python or any other software libraries or dependencies used in the experiments.
Experiment Setup No The paper states that 'The supplementary materials include details of the model and optimization hyperparameters' but these details are not provided within the main text of the paper itself.