Affine-Invariant Online Optimization and the Low-rank Experts Problem
Authors: Tomer Koren, Roi Livni
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present a new affine-invariant optimization algorithm called Online Lazy Newton. The regret of Online Lazy Newton is independent of conditioning: the algorithm s performance depends on the best possible preconditioning of the problem in retrospect and on its intrinsic dimensionality. As an application, we show how Online Lazy Newton can be used to achieve an optimal regret of order r T for the low-rank experts problem, improving by a r factor over the previously best known bound and resolving an open problem posed by Hazan et al. [15]. |
| Researcher Affiliation | Collaboration | Tomer Koren Google Brain 1600 Amphitheatre Pkwy Mountain View, CA 94043 tkoren@google.com Roi Livni Princeton University 35 Olden St. Princeton, NJ 08540 rlivni@cs.princeton.edu |
| Pseudocode | Yes | Algorithm 1 OLN: Online Lazy Newton |
| Open Source Code | No | The paper does not provide any statement or link indicating that source code for the described methodology is publicly available. |
| Open Datasets | No | This is a theoretical paper focused on algorithm design and proofs of regret bounds. It does not involve training models on datasets, so no dataset availability information is provided. |
| Dataset Splits | No | This is a theoretical paper that does not present empirical experiments. Therefore, no dataset split information (training, validation, test) is provided. |
| Hardware Specification | No | This is a theoretical paper focused on algorithm design and analysis. It does not discuss any hardware used for experiments. |
| Software Dependencies | No | This is a theoretical paper focused on algorithm design and analysis. It does not mention any specific software dependencies or version numbers. |
| Experiment Setup | No | This is a theoretical paper and does not describe any empirical experimental setup, hyperparameters, or training configurations. |