Margins, Kernels and Non-linear Smoothed Perceptrons

Authors: Aaditya Ramdas, Javier Peña

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We derive an accelerated smoothed algorithm with a convergence rate of log n / ρ given n separable points, which is strikingly similar to the classical kernelized Perceptron algorithm whose rate is 1/ρ^2. When no such classifier exists, we prove a version of Gordan s separation theorem for RKHSs, and give a reinterpretation of negative margins.
Researcher Affiliation Academia Aaditya Ramdas ARAMDAS@CS.CMU.EDU Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213 USA Javier Pe na JFP@ANDREW.CMU.EDU Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213 USA
Pseudocode Yes Algorithm 1 Perceptron ... Algorithm 2 Normalized Perceptron ... Algorithm 3 Normalized Kernel Perceptron (NKP) ... Algorithm 4 Smoothed Normalized Kernel Perceptron ... Algorithm 5 Normalized Von-Neumann (NVN) ... Algorithm 6 Smoothed Normalized Kernel Perceptron Von Neumann (SNKPV N(q, δ)) ... Algorithm 7 Iterated Smoothed Normalized Kernel Perceptron-Von Neumann (ISNKPV N(γ, ϵ))
Open Source Code No The paper does not contain any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets No The paper focuses on theoretical contributions and does not mention the use of any datasets for training or evaluation. Therefore, no information about public dataset availability is provided.
Dataset Splits No The paper is theoretical and does not describe any dataset splits (training, validation, test) for reproducibility.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or the specific hardware used for computations.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers required for reproducibility.
Experiment Setup No The paper is theoretical and does not describe an experimental setup, hyperparameters, or training configurations.