Smooth Convex Optimization Using Sub-Zeroth-Order Oracles

Authors: Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu3815-3822

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The results of this paper are theoretical.
Researcher Affiliation Academia Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu The University of Texas at Austin, Austin, TX {karabag, cneary, utopcu}@utexas.edu
Pseudocode Yes Algorithm 1 The optimization algorithm OPTIMIZEDP(X, ψDP) for the directional preference oracle; Function PD-DP(x, θ, TA,x); Function COMPARE-DP(X, ε); Algorithm 2 The optimization algorithm OPTIMIZE-C(ε) for the comparator oracle; Function FDD-C(A, x0, d, t); Function PD-C(x, θ, A, t); Algorithm 3 The low regret algorithm REGRET-NV(T, δ)
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper is theoretical and does not involve training data or experiments with datasets.
Dataset Splits No The paper is theoretical and does not involve dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe experiments that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not describe experiments that would require specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not present experimental setup details such as hyperparameters or training configurations.