Beyond Greedy Ranking: Slate Optimization via List-CVAE

Authors: Ray Jiang, Sven Gowal, Yuqiu Qian, Timothy Mann, Danilo J. Rezende

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

Reproducibility Variable Result LLM Response
Research Type Experimental 4 EXPERIMENTS
Researcher Affiliation Collaboration Google Deep Mind, London, UK. The University of Hong Kong
Pseudocode No The paper describes the model architecture and process in text and diagrams, but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology.
Open Datasets Yes Due to a lack of publicly available large scale slate datasets, we use the data provided by the Rec Sys 2015 YOOCHOOSE Challenge (Ben-Shimon et al., 2015).
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits (e.g., percentages or sample counts) needed for reproduction. It mentions using 'uniformly randomly generated slates' for simulation and '100,000 sampled output slates for evaluation purposes' but no clear formal splits.
Hardware Specification No The paper mentions training on '1 GPU' but does not provide specific details such as the model, manufacturer, or other hardware specifications for the experimental setup.
Software Dependencies No The paper does not provide specific software names with version numbers for dependencies such as libraries, frameworks, or solvers used in the experiments.
Experiment Setup Yes For List-CVAE... we fixed the width of all hidden layers to 128, the learning rate to 10 3 and the number of latent dimensions to 16.