Reparameterizing Mirror Descent as Gradient Descent

Authors: Ehsan Amid, Manfred K. K. Warmuth

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our construction for the reparameterization argument is done for the continuous versions of the updates. Finding general criteria for the discrete versions to closely track their continuous counterparts remains an interesting open problem.
Researcher Affiliation Industry Ehsan Amid and Manfred K. Warmuth Google Research, Brain Team Mountain View, CA {eamid, manfred}@google.com
Pseudocode No The paper provides mathematical derivations and theorems but no pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the described methodology. No links or explicit statements about code release are present.
Open Datasets No The paper is theoretical and does not report on experiments using datasets.
Dataset Splits No The paper is theoretical and does not report on experiments or dataset splits.
Hardware Specification No The paper is theoretical and does not involve empirical experiments, thus no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not involve empirical experiments, thus no software dependencies are listed.
Experiment Setup No The paper is theoretical and does not involve empirical experiments, thus no experimental setup details like hyperparameters are provided.