Adaptive Principal Component Regression with Applications to Panel Data
Authors: Anish Agarwal, Keegan Harris, Justin Whitehouse, Steven Z. Wu
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide the first time-uniform finite sample guarantees for online (regularized) PCR whenever data is collected adaptively. Since the proof techniques for analyzing PCR in the fixed design setting do not readily extend to the online setting, our results rely on adapting tools from modern martingale concentration to the error-in-variables setting. As an application of our bounds, we provide a framework for experiment design in panel data settings when interventions are assigned adaptively. |
| Researcher Affiliation | Academia | Anish Agarwal Department of IEOR Columbia University New York, NY 10027 aa5194@columbia.edu Keegan Harris School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 keeganh@cs.cmu.edu Justin Whitehouse School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 jwhiteho@cs.cmu.edu Zhiwei Steven Wu School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 zhiweiw@cs.cmu.edu |
| Pseudocode | No | The paper describes the 'Adaptive Principal Component Regression' procedure in Definition 3.4 in paragraph form, but it does not present it as a structured pseudocode block or algorithm. |
| Open Source Code | No | The paper does not contain any statements about releasing its own source code, nor does it provide a link to a code repository. |
| Open Datasets | No | The paper does not describe empirical experiments with a specific dataset. It presents theoretical results and an application framework, but no actual dataset is used or made publicly available for training. |
| Dataset Splits | No | The paper does not describe empirical experiments with data, and therefore, no training, validation, or test dataset splits are provided. |
| Hardware Specification | No | The paper does not describe any specific hardware (e.g., GPU models, CPU types, cloud instances) used for running experiments, as it is a theoretical paper. |
| Software Dependencies | No | The paper does not mention any specific software dependencies or their version numbers required for replication (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4). |
| Experiment Setup | No | The paper focuses on theoretical derivations and an application framework. It does not provide details on experimental setup, hyperparameters, or system-level training settings, as it does not describe empirical experiments. |