Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff

Authors: Ofer Dekel, Ronen Eldan, Tomer Koren

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present an efficient algorithm for the bandit smooth convex optimization problem that guarantees a regret of e O(T 5/8). Our result rules out an (T 2/3) lower bound and takes a significant step towards the resolution of this open problem. We prove the following regret bound for this algorithm. Theorem 9. We conclude the paper by stating our main lemmas and sketching the proof Lemma 11. The full technical proofs are all deferred to the supplementary material
Researcher Affiliation Collaboration Ofer Dekel Microsoft Research Redmond, WA oferd@microsoft.com Ronen Eldan Weizmann Institute Rehovot, Israel roneneldan@gmail.com Tomer Koren Technion Haifa, Israel tomerk@technion.ac.il
Pseudocode Yes Algorithm 1: Bandit Smooth Convex Optimization
Open Source Code No The paper does not provide any statement or link indicating that its source code is publicly available.
Open Datasets No The paper is theoretical and does not use or refer to any specific publicly available datasets.
Dataset Splits No The paper is theoretical and does not involve dataset splits (training, validation, test).
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and describes algorithmic parameters rather than specific experimental setup details like hyperparameters or training configurations.