Tensor Monte Carlo: Particle Methods for the GPU era

Authors: Laurence Aitchison

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We show that TMC is superior to IWAE on a generative model with multiple stochastic layers trained on the MNIST handwritten digit database, and we show that TMC can be combined with standard variance reduction techniques.
Researcher Affiliation Academia Laurence Aitchison University of Bristol Bristol, UK laurence.aitchison@gmail.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described, nor does it explicitly state that code is being released.
Open Datasets Yes Finally, we do experiments on VAE s with multiple stochastic layers trained on the MNIST handwritten digit database.
Dataset Splits No The paper states training was done on the MNIST handwritten digit database, but does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and test sets.
Hardware Specification Yes The time required for computing marginal likelihood estimates in A on a single Titan X GPU.
Software Dependencies No The paper mentions 'Py Torch' and 'Adam optimizer' but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes In all experiments, we used the Adam optimizer (Kingma & Ba, 2014) using the Py Torch default hyperparameters, and weight normalization (Salimans & Kingma, 2016) to improve numerical stability. We used leaky-relu nonlinearities everywhere except for the standard-deviations (Sønderby et al., 2016), for which we used 0.01+softplus(x), to improve numerical stability by ensuring that the standard deviations could not become too small.