Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Authors: Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of the fat shattering dimension for PAC learnability and the necessity of finiteness of the scaled Natarajan dimension, but little progress had been made towards a more complete characterization since the work of Simon (SICOMP 97).
Researcher Affiliation Collaboration Idan Attias Ben-Gurion University of the Negev idanatti@post.bgu.ac.il Steve Hanneke Purdue University steve.hanneke@gmail.com Alkis Kalavasis Yale University alvertos.kalavasis@yale.edu Amin Karbasi Yale University, Google Research amin.karbasi@yale.edu Grigoris Velegkas Yale University grigoris.velegkas@yale.edu
Pseudocode Yes Algorithm 1 From orientation 𝜎to learner A𝜎; Algorithm 2 Med Boost; Algorithm 3 Scaled SOA
Open Source Code No The paper does not contain any explicit statement about making its source code available, nor does it provide any links to a code repository.
Open Datasets No The paper is theoretical and focuses on mathematical characterizations of learnability; it does not conduct experiments on real-world datasets, nor does it mention any publicly available or open datasets for training purposes.
Dataset Splits No The paper is theoretical and does not describe empirical experiments or data, therefore it does not specify any training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not describe any empirical experiments, therefore it does not specify any hardware used for computations.
Software Dependencies No The paper is theoretical and does not describe any empirical experiments; thus, it does not list any specific software dependencies or version numbers.
Experiment Setup No The paper is theoretical and does not describe any empirical experiments; therefore, it does not provide details about an experimental setup, hyperparameters, or system-level training settings.