Variational Inference for Sequential Data with Future Likelihood Estimates

Authors: Geon-Hyeong Kim, Youngsoo Jang, Hongseok Yang, Kee-Eung Kim

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In Section 6, we report experimental results of our estimator with synthetic and polyphonic music datasets, to show its effectiveness compared to the state-of-the-art algorithms.
Researcher Affiliation Academia 1School of Computing, KAIST, Daejeon, Republic of Korea 2Graduate School of AI, KAIST, Daejeon, Republic of Korea.
Pseudocode No The paper describes its algorithm and methods through text and mathematical equations, but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the described methodology.
Open Datasets Yes We further conducted experiments on real-world datasets using four polyphonic music datasets (Boulanger lewandowski et al., 2012).
Dataset Splits No The paper mentions using validation performance for model selection but does not provide specific details on the dataset splits (e.g., percentages or exact counts for train/validation/test).
Hardware Specification No The paper does not provide specific details on the hardware used for running its experiments, such as GPU/CPU models or memory specifications.
Software Dependencies No The paper mentions the use of PyTorch for implementation but does not specify its version number or other software dependencies with specific versions.
Experiment Setup Yes We used four and eight particles for each algorithm. As for the learning rate, we report the best results among the choices in {3 10 4 , 1 10 4 , 3 10 5 , 1 10 5}.