An equivalence between high dimensional Bayes optimal inference and M-estimation

Authors: Madhu Advani, Surya Ganguli

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We numerically demonstrate superior performance of our optimal M-estimators relative to MAP. Overall, at the heart of our work is the revelation of a remarkable equivalence between two seemingly very different computational problems: namely that of high dimensional Bayesian integration underlying MMSE inference, and high dimensional convex optimization underlying M-estimation. In essence we show that the former difficult integral may be computed by solving the latter, simpler optimization problem. In Section 4, we also demonstrate, through numerical simulations, a substantial performance improvement in inference accuracy achieved by the optimal M-estimator over MAP under nonlinear measurements with non-additive noise.
Researcher Affiliation Academia Madhu Advani Surya Ganguli Department of Applied Physics, Stanford University msadvani@stanford.edu and sganguli@stanford.edu
Pseudocode No The paper describes algorithms (m AMP, b AMP, g AMP) using mathematical equations and textual descriptions, but it does not present any structured pseudocode or an algorithm block explicitly labeled as such.
Open Source Code No The paper does not provide any explicit statements or links about open-sourcing the code for the described methodology.
Open Datasets No The paper uses "simulated data generated as in (1), with dense i.i.d Gaussian measurements" and does not refer to any publicly available datasets.
Dataset Splits No The paper uses simulated data but does not specify any training, validation, or test dataset splits, percentages, or absolute counts. It mentions varying "measurement density α = N/P".
Hardware Specification No The paper does not provide any specific details about the hardware used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies (e.g., library names with version numbers) needed to replicate the experiments.
Experiment Setup Yes The paper specifies the data generation: "simulated data generated as in (1), with dense i.i.d Gaussian measurements." It also states: "For these finite simulated data sets, we varied α = N/P , while holding NP 250."