Convex Two-Layer Modeling with Latent Structure

Authors: Vignesh Ganapathiraman, Xinhua Zhang, Yaoliang Yu, Junfeng Wen

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental Results To empirically evaluate our convex method (henceforth referred to as CVX), we compared it with the state-of-the-art methods on two prediction problems with latent structure. ... The test MRR is shown in Figure 1... The error of inpainting given by the two methods is shown in Table 1...
Researcher Affiliation Academia University of Illinois at Chicago, Chicago, IL, USA University of Waterloo, Waterloo, ON, Canada, University of Alberta, Edmonton, AB, Canada
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. It describes mathematical formulations and optimization schemes in paragraph form.
Open Source Code No The paper does not provide any concrete access to source code (e.g., repository link, explicit code release statement) for the methodology described.
Open Datasets Yes The first experiment is based on the English-Hebrew corpus [35]. ... [35] https://cogcomp.cs.illinois.edu/page/resource_view/2. ... Our second experiment used structured latent model to inpaint images. ...sampled from the MNIST dataset...
Dataset Splits Yes It consists of 250 positive transliteration pairs for training, and 300 pairs for testing. ... We generated 200 sequences of images for training... 200 test sequences were also generated.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. Vague terms like 'on a GPU' are also not present.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes Our method (with σ = 0.1)... Both methods employ an output loss function max{0, yf}2 with y {+1, 1}, and both contain only one parameter the bound on u (and r ). We simply tuned it to optimize the performance of Local. ... We set σ to 10 1 and G( ) = 1 2 2 (Gaussian). ... For both methods, the radius bound was simply chosen as the maximum L2 norm of the images, which produced consistently good results.