The Performance Analysis of Generalized Margin Maximizers on Separable Data

Authors: Fariborz Salehi, Ehsan Abbasi, Babak Hassibi

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our theoretical results are validated by extensive simulation results across a range of parameter values, problem instances, and model structures.
Researcher Affiliation Academia 1Department of Electrical Engineering, California Institute of Technology, Pasadena, California, USA. Correspondence to: Fariborz Salehi <fsalehi@caltech.com>.
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described.
Open Datasets No The paper describes that data for simulations is 'generated from a logistic-type model with the underlying parameter w Rp' and 'drawn independently from the Gaussian distribution'. It does not refer to or provide access to a pre-existing public dataset.
Dataset Splits No The paper does not specify any train/validation/test dataset splits. It discusses 'training data' and 'test data' but not their partitioning or sizes.
Hardware Specification No The paper does not provide any specific details about the hardware used for conducting the numerical simulations.
Software Dependencies No The paper does not mention any specific software dependencies with version numbers.
Experiment Setup Yes The empirical result is the average over 20 trials with p = 150... (Figure 1 caption). For the numerical simulations, the result is the average over 100 independent trials with p = 200 and κ = 2. (Figure 2 caption). The empirical result is the average over 100 trials with p = 200, s = 0.1, and κ = 2. (Figure 3 caption).