Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints

Authors: Jayadev Acharya, Clément L Canonne, Ziteng Sun, Himanshu Tyagi

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main focus is on information-theoretic lower bounds for the minimax error rates (or, equivalently, the sample complexity) of these problems. and We provide a unified framework enabling us to derive a variety of (tight) minimax lower bounds for different parametric families of distributions, both continuous and discrete, under any ℓp loss.
Researcher Affiliation Collaboration Jayadev Acharya Cornell University acharya@cornell.edu Clément L. Canonne University of Sydney clement.canonne@sydney.edu.au Ziteng Sun Google Research, New York zitengsun@google.com Himanshu Tyagi Indian Institute of Science, Bangalore htyagi@iisc.ac.in
Pseudocode Yes Algorithm 1 LDP protocol for mean estimation for the product of Bernoulli family and Algorithm 2 ℓ-bit protocol for estimating product of Bernoulli family
Open Source Code No The paper does not provide any explicit statements or links indicating the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not conduct experiments on datasets, thus it does not mention public datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets, therefore it does not discuss training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not describe computational experiments or the hardware used to perform them. Therefore, no hardware specifications are provided.
Software Dependencies No The paper is theoretical and focuses on mathematical proofs and algorithms, not specific software implementations. Therefore, no software dependencies with version numbers are listed.
Experiment Setup No The paper is theoretical and focuses on mathematical frameworks and algorithms, not practical experimental setups. Therefore, no specific details like hyperparameters or system-level training settings are provided.