SDCA without Duality, Regularization, and Individual Convexity

Authors: Shai Shalev-Shwartz

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove linear convergence rates even if individual loss functions are non-convex, as long as the expected loss is strongly convex.
Researcher Affiliation Academia Shai Shalev-Shwartz SHAIS@CS.HUJI.AC.IL School of Computer Science and Engineering, The Hebrew University of Jerusalem, Israel
Pseudocode Yes Algorithm 1: Dual-Free SDCA for Regularized Objectives
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper focuses on theoretical analysis of algorithms and does not describe experiments with specific datasets, thus no access information for training data is provided.
Dataset Splits No The paper focuses on theoretical analysis and does not describe experiments requiring dataset splits.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware for execution.
Software Dependencies No The paper is theoretical and does not discuss software implementations or their specific version dependencies.
Experiment Setup No The paper is theoretical and describes algorithms and their analysis, but it does not detail an experimental setup or hyperparameters for empirical evaluation.