PulseAugur
EN
LIVE 13:24:26

New private Thompson Sampling algorithm boosts contextual bandit performance

By PulseAugur Editorial · [3 sources] ·

Researchers have developed AdaPrivate-TS, a new differentially private contextual bandit algorithm that integrates Thompson Sampling with batched zCDP composition. This approach interprets the added Gaussian noise as increased uncertainty, leading to improved performance and privacy guarantees. Experiments on various datasets show AdaPrivate-TS achieves high percentages of non-private performance at different privacy budgets and outperforms other baselines, particularly when privacy amplification is applied. AI

IMPACT Enhances privacy in reinforcement learning applications, potentially enabling more sensitive data use in personalized systems.

RANK_REASON The cluster contains a research paper detailing a new algorithm for contextual bandits with differential privacy. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New private Thompson Sampling algorithm boosts contextual bandit performance

COVERAGE [3]

  1. arXiv cs.LG TIER_1 English(EN) · AmirHossein Naghdi, Ali Baheri ·

    Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits

    arXiv:2606.23933v1 Announce Type: cross Abstract: We study non-stationary linear contextual bandits where the reward model drifts over time, rendering classical contextual bandit algorithms brittle because historical data becomes systematically biased. We propose Flow-Corrected T…

  2. arXiv cs.LG TIER_1 English(EN) · Ali Baheri ·

    Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits

    We study non-stationary linear contextual bandits where the reward model drifts over time, rendering classical contextual bandit algorithms brittle because historical data becomes systematically biased. We propose Flow-Corrected Thompson Sampling (fcTS), a Bayesian method that re…

  3. arXiv stat.ML TIER_1 English(EN) · Eranga Ukwatta ·

    AdaPrivate-TS: Private Thompson Sampling for Contextual Bandits with Privacy Amplification

    We present AdaPrivate-TS, a differentially private contextual bandit algorithm that combines Thompson Sampling with batched zCDP composition. Our key insight is that differential privacy noise inflates the posterior covariance in a structured way: adding Gaussian noise $N(0,σ^2 I…

RELATED ENTITIES

RELATED TOPICS