Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

Authors: Yuyang Deng, Ilja Kuzborskij, Mehrdad Mahdavi

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To demonstrate the effectiveness of our proposed mixture weights estimation algorithm, we conducted an experiment using MNIST dataset [1] according to the following specifications.
Researcher Affiliation Collaboration Yuyang Deng Pennsylvania State University yzd82@psu.edu Ilja Kuzborskij Google Deep Mind iljak@google.com Mehrdad Mahdavi Pennsylvania State University mzm616@psu.edu
Pseudocode Yes Algorithm 1: Mixture Weight Estimation; Algorithm 2: Learning w function by a neural network; Algorithm 3: GD(v, α, K); Algorithm 4: Label efficient nonparametric online regression
Open Source Code No The paper does not provide any statement about making its source code available or include a link to a code repository for its proposed methods.
Open Datasets Yes To demonstrate the effectiveness of our proposed mixture weights estimation algorithm, we conducted an experiment using MNIST dataset [1]...
Dataset Splits No The paper mentions 80 for training and 20 for testing samples for each domain but does not explicitly state a validation split. No specific percentages or counts are provided for a validation set.
Hardware Specification No The paper does not specify the hardware used for running the experiments, such as CPU or GPU models, or memory.
Software Dependencies No The paper mentions implementing experiments with a "two-layer MLP neural network" but does not specify any software libraries (e.g., TensorFlow, PyTorch) or their version numbers.
Experiment Setup No The paper mentions using a "two-layer MLP neural network" but does not provide specific hyperparameters such as learning rates, batch sizes, or optimizer details used in the experimental setup.