Online Improper Learning with an Approximation Oracle

Authors: Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our results are summarized in Table 1 below. We present these two algorithms and their guarantees in Sections 3 and Appendix B.
Researcher Affiliation Collaboration Elad Hazan Princeton University & Google AI Princeton ehazan@cs.princeton.edu Wei Hu Princeton University huwei@cs.princeton.edu Yuanzhi Li Stanford University yuanzhil@stanford.edu Zhiyuan Li Princeton University zhiyuanli@cs.princeton.edu
Pseudocode Yes Algorithm 1 Online Mirror Descent using a Projection-and-Separation Oracle; Algorithm 2 Projection-and-Decomposition Oracle, PAD(y, , W, '); Algorithm 3 Online Stochastic Mirror Descent with Barycentric Regularization
Open Source Code No The paper does not provide any statements about releasing its own source code or links to a code repository.
Open Datasets No The paper is theoretical and does not conduct experiments on specific datasets, so no dataset availability information for training is provided.
Dataset Splits No The paper does not discuss empirical validation or dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe running experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and focuses on algorithms and proofs; it does not mention any specific software dependencies with version numbers for implementation.
Experiment Setup No The paper is theoretical and does not describe an empirical experimental setup with hyperparameters or system-level training settings.