Universal Rates for Interactive Learning

Authors: Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Researcher Affiliation Collaboration Steve Hanneke Purdue University steve.hanneke@gmail.com Amin Karbasi Yale University, Google Research amin.karbasi@yale.edu Shay Moran Technion, Google Research smoran@technion.ac.il Grigoris Velegkas Yale University grigoris.velegkas@yale.edu
Pseudocode Yes Figure 2: Arbitrarily Fast Rates Algorithm; Figure 3: Interactive Learning with Partial Concept Classes; Figure 4: Exponential Rates Algorithm; Figure 5: Aggregate Function Subroutine
Open Source Code No 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No The paper describes a theoretical framework involving 'unlabeled data points from X that are drawn i.i.d. from PX' as part of its model, but does not refer to specific publicly available datasets or provide access information for empirical training data.
Dataset Splits No The paper is purely theoretical and does not involve empirical experiments or dataset evaluations, thus no validation dataset splits are provided.
Hardware Specification No The paper is theoretical and does not conduct empirical experiments, therefore no hardware specifications are mentioned. The reproducibility checklist states N/A for hardware.
Software Dependencies No The paper is theoretical and does not conduct empirical experiments, therefore no specific software dependencies with version numbers are mentioned. The reproducibility checklist states N/A for software.
Experiment Setup No The paper is purely theoretical and does not include empirical experiments, thus no experimental setup details like hyperparameters or training configurations are provided.