Agnostically Learning Single-Index Models using Omnipredictors

Authors: Aravind Gollakota, Parikshit Gopalan, Adam Klivans, Konstantinos Stavropoulos

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our analysis is simple and relies on the relationship between Bregman divergences (or matching losses) and ℓp distances. We also provide new guarantees for standard algorithms like GLMtron and logistic regression in the agnostic setting. Our main result is the first efficient learning algorithm with a guarantee of this form.
Researcher Affiliation Collaboration Aravind Gollakota Apple Parikshit Gopalan Apple Adam R. Klivans UT Austin Konstantinos Stavropoulos UT Austin
Pseudocode Yes Algorithm 1: Calibrated Multiaccuracy (modification of Algorithm 2 in Gopalan et al. [2023])
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not use or describe a specific public dataset for empirical evaluation. It refers to abstract 'distributions' rather than concrete datasets.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets, thus no dataset split information (train/validation/test) is provided.
Hardware Specification No The paper focuses on theoretical aspects and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers required for reproducibility.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations for empirical evaluation.