Task-based End-to-end Model Learning in Stochastic Optimization

Authors: Priya Donti, Brandon Amos, J. Zico Kolter

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present three experimental evaluations of the proposed approach: a classical inventory stock problem, a real-world electrical grid scheduling task, and a real-world energy storage arbitrage task. We show that the proposed approach can outperform both traditional modeling and purely black-box policy optimization approaches in these applications.
Researcher Affiliation Academia Priya L. Donti Dept. of Computer Science Dept. of Engr. & Public Policy Carnegie Mellon University Pittsburgh, PA 15213 pdonti@cs.cmu.edu Brandon Amos Dept. of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 bamos@cs.cmu.edu J. Zico Kolter Dept. of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 zkolter@cs.cmu.edu
Pseudocode Yes Algorithm 1 Task Loss Optimization
Open Source Code Yes Source code for all experiments is available at https://github.com/locuslab/e2e-model-learning.
Open Datasets No The paper uses "real electrical grid data" but does not provide a specific link, DOI, or common name for public access to these datasets.
Dataset Splits No The paper specifies train and test data periods (e.g., "7 years of data to train the model, and 1.75 subsequent years for testing"), but does not explicitly mention or detail a separate validation split or set for hyperparameter tuning.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, TensorFlow 2.x, PyTorch 1.x).
Experiment Setup Yes We employ a 2-hidden-layer neural network for this purpose, with an additional residual connection from the inputs to the outputs initialized to the linear regression solution.