Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization

Authors: Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi

NeurIPS 2022 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We included a .ipynb file to reproduce the experimental results.
Researcher Affiliation Academia Tesi Xiao Department of Statistics University of California, Davis EMAIL Krishnakumar Balasubramanian Department of Statistics University of California, Davis EMAIL Saeed Ghadimi Department of Management Sciences University of Waterloo EMAIL
Pseudocode Yes Algorithm 1 Linearized NASA with Inexact Conditional Gradient Method (Li NASA+ICG)
Open Source Code Yes We included a .ipynb file to reproduce the experimental results.
Open Datasets No The paper does not explicitly mention or provide access information for any publicly available datasets used in experiments. It describes theoretical algorithms with stochastic oracles.
Dataset Splits No The paper does not provide specific train/validation/test dataset splits, as it primarily focuses on theoretical analysis and algorithm design without detailing specific empirical experiments on datasets.
Hardware Specification No The paper does not provide any specific hardware specifications used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers needed to replicate the experiment.
Experiment Setup No The paper provides theoretical definitions for algorithm parameters (e.g., τk, ÎČk), but it does not specify concrete hyperparameter values or system-level training settings for an experimental setup.