Horizon-Independent Minimax Linear Regression
Authors: Alan Malek, Peter L. Bartlett
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We show that, once provided with a measure of the scale of the problem, we can invert the recursion and play the minimax strategy without knowing the future covariates. Further, we show that this forward recursion remains optimal even against adaptively chosen labels and covariates, provided that the adversary adheres to a set of constraints that prevent misrepresentation of the scale of the problem. |
| Researcher Affiliation | Academia | Alan Malek Laboratory for Information and Decision Systems Massachusetts Institute of Technology 77 Massachusetts Avenue Cambridge, MA 02139-4307, USA amalek@mit.edu Peter L. Bartlett Department of EECS and Statistics University of California Berkeley, CA 94720-1776, USA bartlett@cs.berkeley.edu |
| Pseudocode | No | The paper describes algorithms using mathematical formulas and text, such as (MMS) and equation (3), but does not provide a formal pseudocode block or algorithm listing. |
| Open Source Code | No | There is no mention of open-source code being released or a link to a repository. The paper is purely theoretical. |
| Open Datasets | No | No datasets are mentioned or used as the paper is purely theoretical. |
| Dataset Splits | No | No dataset splits are mentioned as no experiments are conducted in the paper. |
| Hardware Specification | No | No specific hardware details are mentioned as no experiments are conducted in the paper. |
| Software Dependencies | No | No software dependencies with version numbers are mentioned as no experiments are conducted in the paper. |
| Experiment Setup | No | No specific experimental setup details, such as hyperparameters or system-level training settings, are provided as no experiments are conducted in the paper. |