Connecting Optimization and Regularization Paths

Authors: Arun Suggala, Adarsh Prasad, Pradeep K. Ravikumar

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we conduct simulations to corroborate our theoretical findings. We use linear regression to empirically verify our results on connecting ridge-regression and gradient descent. We also corroborate our findings on excess risk and optimality of early-stopping rule for gradient descent.
Researcher Affiliation Academia Arun Sai Suggala Carnegie Mellon University Pittsburgh, PA 15213 asuggala@cs.cmu.edu Adarsh Prasad Carnegie Mellon University Pittsburgh, PA 15213 adarshp@cs.cmu.edu Pradeep Ravikumar Carnegie Mellon University Pittsburgh, PA 15213 pradeepr@cs.cmu.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper describes simulating data rather than using a publicly available or open dataset with access information. 'We simulate a linear model by drawing the covariates from an isotropic gaussian X N(0, Ip p) and the response y|x N( T x, σ2)' and 'We construct a classification dataset by drawing covariates X from isotropic gaussian i.e. X N(0, Ip).'
Dataset Splits No The paper describes how the data was simulated but does not provide specific dataset split information for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes We generate a sequence of iterates by GD with step size 0.01... We fix p = 100 and vary the samples n from 100 to 1500... We run GD with a step size = 0.123 and construct corresponding points on the regularization path ( (t) = t )... We fix the dimension p = 128 and the number of samples to n = 32.