StopWasting My Gradients: Practical SVRG

Authors: Reza Babanezhad Harikandeh, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we present experimental results that evaluate our proposed variations on the SVRG method.
Researcher Affiliation Academia Department of Computer Science University of British Columbia, School of Mathematics University of Edinburgh, Department of Electrical and Computer Engineering University of British Columbia
Pseudocode Yes Algorithm 1 Batching SVRG, Algorithm 2 Mixed SVRG and SG Method, Algorithm 3 Heuristic for skipping evaluations of fi at x
Open Source Code No The paper does not contain an explicit statement about releasing its source code or a link to a code repository.
Open Datasets Yes We consider the datasets used by [1], whose properties are listed in the supplementary material.
Dataset Splits No The paper refers to datasets used by [1] and their properties in the supplementary material but does not explicitly provide specific training, validation, and test split information within the main text.
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 does not provide specific software dependencies with version numbers.
Experiment Setup Yes As in their work we add a bias variable, normalize dense features, and set the regularization parameter λ to 1/n. We used a step-size of α = 1/L and we used m = |Bs| which gave good performance across methods and datasets.