Second-Order Kernel Online Convex Optimization with Adaptive Sketching
Authors: Daniele Calandriello, Alessandro Lazaric, Michal Valko
ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The paper primarily focuses on introducing new algorithms (KONS, SKETCHED-KONS), deriving theoretical regret bounds (e.g., O(deff log T)), analyzing computational complexity, and presenting theoretical properties (Theorems, Lemmas, Algorithms 1, 2, 3). There are no sections dedicated to empirical studies, dataset evaluations, performance metrics, or experimental results that would indicate an experimental research design. |
| Researcher Affiliation | Academia | Daniele Calandriello 1 Alessandro Lazaric 1 Michal Valko 1 1Seque L team, INRIA Lille Nord Europe. Correspondence to: Daniele Calandriello <daniele.calandriello@inria.fr>. |
| Pseudocode | Yes | Algorithm 1 One-shot KONS Algorithm 2 Kernel Online Row Sampling (KORS) Algorithm 3 SKETCHED-KONS |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described. |
| Open Datasets | No | The paper is theoretical and does not describe or refer to any datasets used for training or other purposes. |
| Dataset Splits | No | The paper is theoretical and does not describe or refer to any dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not discuss hardware specifications as no experiments were conducted. |
| Software Dependencies | No | The paper is theoretical and does not list any specific software dependencies with version numbers for reproducing experiments. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings. |