Kernel Implicit Variational Inference

Authors: Jiaxin Shi, Shengyang Sun, Jun Zhu

ICLR 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present empirical results on both synthetic and real datasets to demonstrate the benefits of KIVI.
Researcher Affiliation Academia Department of Computer Science & Technology, THU Lab for Brain and AI, Tsinghua University Department of Computer Science, University of Toronto
Pseudocode Yes Algorithm 1 Kernel Implicit Variational Inference (KIVI) and Algorithm 2 MMNN
Open Source Code No The paper mentions that 'All implementations are based on Zhu Suan (Shi et al., 2017)', which is cited as 'A library for Bayesian deep learning'. However, it does not provide a direct link or explicit statement that the code for this specific paper's methodology is open-source or available.
Open Datasets Yes We present empirical results on both synthetic and real datasets... for regression benchmarks... Boston, Concrete, Energy, Kin8nm, Naval, Combined, Protein, Wine, Yacht, Year... We conduct experiments on two widely used datasets for generative modeling: binarized MNIST and Celeb A (Liu et al., 2015).
Dataset Splits Yes We used the last 10,000 samples of the training set as the validation set for model selection.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or computational resources) used for running the experiments.
Software Dependencies No The paper mentions 'All implementations are based on Zhu Suan (Shi et. al., 2017)', but no version numbers are provided for Zhu Suan or any other software dependencies.
Experiment Setup Yes For all datasets, we set np = nq = M = 100, λ = 0.001 and set the batch size to 100 and the learning rate to 0.001. The model is trained for 3000 epochs for the small datasets with less than 1000 data points, and 500 epochs for the others.