Better Full-Matrix Regret via Parameter-Free Online Learning
Authors: Ashok Cutkosky
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide online convex optimization algorithms that guarantee improved fullmatrix regret bounds. These algorithms extend prior work in several ways. First, we seamlessly allow for the incorporation of constraints without requiring unknown oracle-tuning for any learning rate parameters. Second, we improve the regret analysis of the full-matrix Ada Grad algorithm by suggesting a better learning rate value and showing how to tune the learning rate to this value on-the-fly. Third, all our bounds are obtained via a general framework for constructing regret bounds that depend on an arbitrary sequence of norms. |
| Researcher Affiliation | Academia | Ashok Cutkosky Department of Electrical and Computer Engineering Boston University Boston, Massachusetts, USA ashok@cutkosky.com |
| Pseudocode | Yes | Algorithm 1 Unconstrained Varying Norms Adaptivity; Algorithm 2 Varying Norms Adaptivity |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | No | This paper is theoretical and does not conduct experiments on datasets, thus no training dataset information is provided. |
| Dataset Splits | No | This paper is theoretical and does not conduct experiments on datasets, thus no validation split information is provided. |
| Hardware Specification | No | This paper is theoretical and does not describe experiments, therefore no hardware specifications are mentioned. |
| Software Dependencies | No | This paper is theoretical and does not describe experiments, therefore no software dependencies with version numbers are mentioned. |
| Experiment Setup | No | This paper is theoretical and does not describe experiments, therefore no experimental setup details like hyperparameters or training settings are provided. |