Fast rates for prediction with limited expert advice
Authors: El Mehdi Saad, Gilles Blanchard
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We investigate the problem of minimizing the excess generalization error... we show that if we are allowed to see the advice of only one expert per round... the worst-case excess risk is Ω(1/T) ... However, if we are allowed to see at least two actively chosen expert advices per training round... the fast rate O(1/T) can be achieved. We design novel algorithms achieving this rate in this setting, and in the setting where the learner has a budget constraint on the total number of observed expert advices, and give precise instance-dependent bounds on the number of training rounds and queries needed to achieve a given generalization error precision. |
| Researcher Affiliation | Academia | El Mehdi Saad1, Gilles Blanchard1,2 1Laboratoire de Mathématiques d Orsay, CNRS, Université Paris-Saclay; 2Inria |
| Pseudocode | Yes | Algorithm 1 Budgeted aggregation; Algorithm 2 Two-point feedback |
| Open Source Code | No | The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper describes theoretical frameworks and algorithms but does not mention the use of any specific dataset for training, nor its public availability. |
| Dataset Splits | No | The paper is theoretical and does not conduct empirical experiments, so it does not describe training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for computations or experiments. |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers required to reproduce the work. |
| Experiment Setup | No | The paper is theoretical and does not describe empirical experiments, therefore no specific experimental setup details such as hyperparameters or training configurations are provided. |