Variational Consensus Monte Carlo
Authors: Maxim Rabinovich, Elaine Angelino, Michael I. Jordan
NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We illustrate the advantages of our algorithm on three inference tasks from the literature, demonstrating both the superior quality of the posterior approximation and the moderate overhead of the optimization step. Our algorithm achieves a relative error reduction (measured against serial MCMC) of up to 39% compared to consensus Monte Carlo on the task of estimating 300-dimensional probit regression parameter expectations; similarly, it achieves an error reduction of 92% on the task of estimating cluster comembership probabilities in a Gaussian mixture model with 8 components in 8 dimensions. |
| Researcher Affiliation | Academia | Maxim Rabinovich, Elaine Angelino, and Michael I. Jordan Computer Science Division University of California, Berkeley {rabinovich, elaine, jordan}@eecs.berkeley.edu |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks with explicit labels like 'Pseudocode' or 'Algorithm'. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described in this paper, nor does it state that code is available in supplementary materials or a repository. |
| Open Datasets | Yes | We run two experiments: the first using a data generating distribution from Scott et al. [22], with N = 8500 data points and d = 5 dimensions, and the second using N = 10^5 data points and d = 300 dimensions. |
| Dataset Splits | No | The paper mentions total dataset sizes and general evaluation metrics, but does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning into training, validation, and test sets. |
| Hardware Specification | No | The paper discusses computational efficiency and runtime but does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. It only mentions 'multicore and multi-machine architectures'. |
| Software Dependencies | No | The paper mentions 'Py Stan implementation of Hamiltonian Monte Carlo (HMC)' for the Mixture of Gaussians model, but it does not specify the version number for PyStan or any other software dependencies. |
| Experiment Setup | Yes | In both cases, we use a form of projected SGD, using 40 samples per iteration to estimate the variational gradients and running 25 iterations of optimization. |