Revisiting $(\epsilon, \gamma, \tau)$-similarity learning for domain adaptation
Authors: Sofiane Dhouib, Ievgen Redko
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper, we propose to extend the theoretical analysis of similarity learning to the domain adaptation setting... We give a new definition of an (ϵ, γ) good similarity for domain adaptation and prove several results quantifying the performance... Section 5 is dedicated to the empirical evaluations of the obtained theoretical results. |
| Researcher Affiliation | Academia | Sofien Dhouib Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69100, LYON, France sofiane.dhouib@creatis.insa-lyon.fr Ievgen Redko Univ Lyon, UJM-Saint-Etienne, CNRS, Institut d Optique Graduate School Laboratoire Hubert Curien UMR 5516, F-42023, Saint-Etienne, France ievgen.redko@univ-st-etienne.fr |
| Pseudocode | No | The paper contains mathematical formulations and algorithms are described in prose, but there is no distinct pseudocode block or clearly labeled algorithm section. |
| Open Source Code | No | The paper does not contain any statement about releasing source code, nor does it provide a link to a code repository. |
| Open Datasets | No | We generate the source domain data as a set of 500 two-dimensional points drawn from a mixture of two Gaussian distributions... The target data is generated from the same distribution as the source data by rotating clusters centers by angles varying from 0 to 90. |
| Dataset Splits | No | The paper describes generating synthetic data and evaluating on the target data, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages, sample counts, or citations to predefined splits). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as GPU models, CPU specifications, or memory. |
| Software Dependencies | No | The paper does not provide specific software dependencies, libraries, or solvers with version numbers that would be required to replicate the experiments. |
| Experiment Setup | Yes | We generate the source domain data as a set of 500 two-dimensional points drawn from a mixture of two Gaussian distributions with the same isotropic covariance matrices σ2I2 and mixing coefficients, where σ is the chosen standard deviation4. Each distribution represents one of the two classes 1 and 1 centered at (1, 1) and ( 1, 1), respectively. The target data is generated from the same distribution as the source data by rotating clusters centers by angles varying from 0 to 90... In the presented results, we set σ = 0.5... The results are computed for a rotation angle θ between 0 and 90 , and after averaging over 30 draws of target samples. |