PulseAugur
EN
LIVE 19:22:54

New adaptive learning rates enhance Follow-the-Perturbed-Leader algorithm

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new adaptive learning rate method for the Follow-the-Perturbed-Leader (FTPL) algorithm in online learning. This approach introduces surrogate probability functions to enable probability-dependent adaptivity without requiring exact probability calculations. The method extends Best-of-Both-Worlds guarantees for FTPL with Pareto perturbations and in expert advice settings, maintaining FTPL's computational efficiency. AI

IMPACT Introduces a novel adaptive learning rate methodology for online learning algorithms, potentially improving performance in bandit and expert advice problems.

RANK_REASON The cluster contains an academic paper detailing a new algorithmic approach.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New adaptive learning rates enhance Follow-the-Perturbed-Leader algorithm

COVERAGE [2]

  1. arXiv stat.ML TIER_1 English(EN) · Jongyeong Lee, Junya Honda, Shinji Ito, Chansoo Kim ·

    Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader

    arXiv:2606.06043v1 Announce Type: new Abstract: Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-s…

  2. arXiv stat.ML TIER_1 English(EN) · Chansoo Kim ·

    Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader

    Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-selection probabilities, obtained by solving conv…

RELATED ENTITIES

RELATED TOPICS