Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Channel Simulation and Distributed Compression with Ensemble Rejection Sampling

Authors: Truong Buu Phan, Ashish Khisti

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The effectiveness of our proposed scheme is validated through experiments involving synthetic Gaussian sources and distributed image compression using the MNIST dataset. ... Section 6 Experiments
Researcher Affiliation Academia Buu Phan1 Ashish Khisti 1 Department of Electrical and Computer Engineering, University of Toronto EMAIL, EMAIL
Pseudocode Yes Algorithm 1: Ensemble Rejection Sampling ERS(W; PY , QY , ω = maxy PY (y) QY (y), scale = 1) ... Algorithm 2: Wyner-Ziv Distributed Compression Protocol
Open Source Code No Code will be included for reproducibility. ... Code will be available upon acceptance.
Open Datasets Yes The effectiveness of our proposed scheme is validated through experiments involving synthetic Gaussian sources and distributed image compression using the MNIST dataset. ... The effectiveness of our proposed scheme is validated through experiments involving synthetic Gaussian sources and distributed image compression using the MNIST dataset. ... with the MNIST dataset[25].
Dataset Splits No The paper uses the MNIST dataset but does not explicitly provide specific training/test/validation splits (e.g., percentages, sample counts, or explicit reference to a named standard split) in the main text or appendices.
Hardware Specification Yes All experiments are conducted on a single NVIDIA RTX A-4500. ... Each model is trained for 30 epochs on an NVIDIA RTX A4500
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions) in the main text or appendices.
Experiment Setup Yes Each model is trained for 30 epochs on an NVIDIA RTX A4500, requiring approximately 30 minutes per model. We use random horizontal flipping and random rotation within the range 15o. We use the following values of β {0.225, 0.28, 0.31, 0.4} that corresponds to the target distortions {6.6, 6.3, 6.1, 5.8} 10 2 in Figure 6.