Shifting Regret, Mirror Descent, and Matrices
Authors: Andras Gyorgy, Csaba Szepesvari
ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Introducing an arbitrary mapping inside the mirror decent algorithm, we provide a framework that unifies and extends existing results. As an example, we prove new shifting regret bounds for matrix prediction problems. |
| Researcher Affiliation | Academia | Andr as Gy orgy A.GYORGY@IMPERIAL.AC.UK Dept. of Electrical and Electronic Engineering, Imperial College London, London, SW7 2BT, UK Csaba Szepesv ari SZEPESVA@UALBERTA.CA Dept. of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8 CANADA |
| Pseudocode | Yes | Algorithm 1 Twisted mirror descent. 1. Set w1 K A . 2. At time t = 1, 2, . . . predict wt, and compute vt+1 = argmin u K A [ηt ℓt(wt), u + DR(u, wt) ] wt+1 = φt+1(vt+1, ℓ1, . . . , ℓt) |
| Open Source Code | No | The paper does not provide any concrete access information for source code. |
| Open Datasets | No | The paper is theoretical and does not describe the use of any datasets, public or otherwise. |
| Dataset Splits | No | The paper is theoretical and does not involve experimental data or dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not specify any software dependencies with version numbers for replication. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training configurations. |