Learning with SGD and Random Features
Authors: Luigi Carratino, Alessandro Rudi, Lorenzo Rosasco
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The obtained results are corroborated and illustrated by numerical experiments. We study the behavior of the SGD with RF algorithm on subsets of n = 2 105 points of the SUSY 3 and HIGGS 4 datasets [43]. |
| Researcher Affiliation | Academia | Luigi Carratino University of Genoa, Genoa, Italy Alessandro Rudi INRIA Sierra Project-team, École Normale Supérieure, Paris Lorenzo Rosasco University of Genoa, LCSL IIT & MIT |
| Pseudocode | No | Insufficient information. The paper provides a mathematical description of the algorithm in Equation (3) but does not include any structured pseudocode or an explicitly labeled algorithm block. |
| Open Source Code | No | Insufficient information. The paper does not contain any statement about releasing source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | We study the behavior of the SGD with RF algorithm on subsets of n = 2 105 points of the SUSY 3 and HIGGS 4 datasets [43]. |
| Dataset Splits | No | Insufficient information. The paper mentions using 'test sets' in the experiments section, but it does not provide specific details about training, validation, and test splits (e.g., percentages, sample counts, or predefined splits). |
| Hardware Specification | Yes | We gratefully acknowledge the support of NVIDIA Corporation for the donation of the Titan Xp GPUs and the Tesla k40 GPU used for this research. |
| Software Dependencies | No | Insufficient information. The paper does not mention any specific software dependencies or their version numbers (e.g., Python, PyTorch, TensorFlow, etc.) used for the experiments. |
| Experiment Setup | Yes | In Figure 3.3 we show the classification error after 5 passes over the data of SGD with RF as the number of RF increases, with a fixed batch size of pn and a step-size of 1... We show in Figure 2 the classification error of SGD with RF after 1 pass over the data, with a fixed number of random features pn, as mini-batch size and step-size vary... |