New algorithms reduce private bandit regret to nearly non-private levels.
problem Differentially private adversarial bandits and expert advice.
method Conversion of non-private algorithms to private, new algorithms for bandits and expert advice.
result Improved regret bounds for private bandits, sublinear for small ε.
Paper develops a private algorithm for multi-agent learning in bandits.
problem Private cooperative learning in decentralized systems.
method Developed extsc{FedUCB} algorithm for multi-agent learning.
result Improves pseudoregret bounds and empirical performance.
Paper tackles LDP bandits learning with improved results and sub-linear regret.
problem Contextual bandits learning with LDP privacy constraints.
method Simple black-box reduction frameworks for context-free bandits, extended to GLB.
result First result for BCO with multi-point feedback under LDP, sub-linear regret for GLB.
Paper proposes no-regret algorithms for private GP bandit optimization.
problem Private Gaussian process bandit optimization.
method Combines uniform kernel approximator with random perturbations for differentially private GP bandit algorithms.
result Provable no-regret algorithms for stationary kernel functions in two DP settings.
This paper achieves optimal regret bounds for locally private linear contextual bandit.
problem Designing locally private linear contextual bandit algorithms with optimal regret bounds.
method New algorithmic and analytical ideas, including mean absolute deviation analysis and layered principal component regression.
result Achieves an i l d e O ( T ) ilde O(\sqrt{T}) i l d e O ( T ) regret upper bound for locally private linear contextual bandit. Study on private and robust multi-armed bandits with contaminated heavy-tailed rewards.
problem Private and robust multi-armed bandits with contaminated heavy-tailed rewards.
method Proposed a meta-algorithm with a private and robust mean estimation sub-routine exttt{PRM}.
result Achieved nearly-optimal regret for two heavy-tailed settings.
New algorithms for private generalized linear contextual bandits.
problem Private estimation and optimization for generalized linear models under differential privacy.
method Developed algorithms for stochastic and adversarial contexts under shuffle and joint differential privacy.
result Achieved private regret bounds for generalized linear models, differing from non-private rates by factors of d / ε \sqrt{d/\varepsilon} d / ε and d / ε \sqrt{d/\varepsilon} d / ε respectively. A privacy-preserving algorithm for high-dimensional bandits.
problem High-dimensional stochastic contextual linear bandits with sparse parameters under privacy constraints.
method PrivateLASSO algorithm based on sparse hard-thresholding and episodic thresholding.
result Minimax private lower bounds and utility guarantees for PrivateLASSO.
Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.
problem Identifying the arm with the highest quantile in multi-armed bandits with private rewards.
method Proposed a (non-private) and differentially private successive elimination algorithms for best-arm identification.
result The proposed algorithms are essentially optimal for quantile bandit problems, with finite sample complexity even for distributions with infinite support-size.
We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided per-round context. Though the context is chosen arbitrarily or adversarially, the reward is assumed…
Paper addresses privacy and robustness in stochastic linear bandits.
problem Stochastic linear bandits with differential privacy and adversarial robustness.
method Logarithmic batch queries, arm elimination algorithm, two privacy models.
result First algorithms providing differential privacy and adversarial robustness.
New algorithm for differential private kernel bandits with improved regret bounds.
problem Contextual bandits with differential privacy constraints.
method Proposes a private kernel-ridge regression estimator using random projections.
result Achieves state-of-the-art cumulative regret bounds in both joint and local models of differential privacy.
We present differentially private algorithms for the stochastic Multi-Armed Bandit (MAB) problem. This is a problem for applications such as adaptive clinical trials, experiment design, and user-targeted advertising where private information is connected to individual rewards. Our major contribution is to show that the…
Proposes a differentially private bandit algorithm reducing noise over time.
problem Privacy concerns in interactive recommendation systems.
method Tree-based mechanism to add Laplace or Gaussian noise to model parameters, focusing on dynamic global sensitivity.
result Demonstrates ( ε , δ ) (ε, δ) ( ε , δ ) -differential privacy with reduced noise and improved regret. The paper addresses private and Byzantine-proof cooperative decision-making in multi-agent systems.
problem Designing algorithms for multi-agent decision-making that are private and resilient to faulty agents.
method Upper-confidence bound algorithms for stochastic bandit problems under privacy and Byzantine conditions.
result Optimal regret achieved in both private and Byzantine-tolerant settings.
Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased downwards --- and when gathering more complicated data --- running hypothesis tests on c…
Paper addresses private online convex optimization with optimal algorithms in various geometries and high-dimensional bandits.
problem Private online convex optimization with streaming and continual release data.
method Proposes a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction.
result Achieves optimal excess risk in linear time for 1 < p ≤ 2 1<p\leq 2 1 < p ≤ 2 and state-of-the-art excess risk for 2 < p ≤ ∞ 2<p\leq\infty 2 < p ≤ ∞ . New method for private linear regression under privacy constraints, achieving optimal rates.
problem Statistical complexity of private linear regression under unknown, ill-conditioned covariates.
method Information-Weighted Regression method
result Optimal convergence rates for both central and local privacy models.
AdaPrivate-TS: A differentially private Thompson Sampling algorithm for contextual bandits
problem Private Thompson Sampling for Contextual Bandits
method Combining Thompson Sampling with batched zCDP composition
result Achieves 93-99% of non-private performance at ε ∈ [0.5, 5] with logarithmic privacy cost
Develops locally private methods for nonparametric contextual bandits.
problem Privacy concerns in sequential decision-making on sensitive data.
method Uniform-confidence-bound-type estimator and jump-start scheme.
result Minimax optimality of proposed methods supported by lower bounds.
New algorithms improve privacy in bandit problems with partial information.
problem Privacy constraints in multi-armed bandit problems with partial reward information.
method Proposed a generic framework for designing ε ε ε -global DP extensions of UCB and KL-UCB algorithms. result AdaP-KLUCB algorithm achieves optimal regret bound under ε ε ε -global DP constraints. Contextual bandit algorithms~(CBAs) often rely on personal data to provide recommendations. Centralized CBA agents utilize potentially sensitive data from recent interactions to provide personalization to end-users. Keeping the sensitive data locally, by running a local agent on the user's device, protects the user's p…
Paper addresses DP in bandits, focusing on zCDP and providing private algorithms.
problem Privacy concerns in recommender systems using user-sensitive data.
method Formalizes and compares different DP adaptations to bandits, proposes private algorithms for various bandit settings.
result Private algorithms ensure negligible privacy costs compared to non-private regret.
Privacy-preserving multi-party contextual bandits learn without sharing data.
problem Privacy-preserving learning for contextual bandits with multiple parties.
method Secure multi-party computation combined with epsilon-greedy differential privacy.
result Developed a privacy-preserving multi-party contextual bandit algorithm.
Paper addresses privacy in combinatorial semi-bandits with improved bounds.
problem Privacy-preserving learning in combinatorial semi-bandits with additional dimension dependence.
method Proposes novel algorithms and proves optimal regret bounds for LDP and DP settings.
result Achieves nearly optimal regret bounds for LDP and DP settings, matching non-private rates.
In this paper we develop the first algorithms for online submodular minimization that preserve differential privacy under full information feedback and bandit feedback. A sequence of T T T submodular functions over a collection of n n n elements arrive online, and at each timestep the algorithm must choose a subset of $[n]…
A model for human-machine decision-making with private info and opacity.
problem Optimizing decisions in a human-machine system with private info and opacity.
method Formulated as a two-player learning problem, proved lower and upper bounds on optimality.
result Simple coordination strategy is nearly minimax optimal, efficient learning possible under certain assumptions.
A new algorithm for differential privacy in kernelized contextual bandits reduces error rate.
problem Joint differential privacy in kernelized contextual bandits.
method Proposes a novel algorithm with a specific error rate and privacy parameter dependence.
result Achieves an error rate of $\mathcal{O}\left(\sqrt{\frac{γ_T}{T}} + \frac{γ_T}{T \varepsilon}
ight)$ after T T T queries. We present a provably optimal differentially private algorithm for the stochastic multi-arm bandit problem, as opposed to the private analogue of the UCB-algorithm [Mishra and Thakurta, 2015; Tossou and Dimitrakakis, 2016] which doesn't meet the recently discovered lower-bound of Ω ( K log ( T ) ε ) Ω\left(\frac{K\log(T)}ε \right) Ω ( ε K l o g ( T ) ) [Shar…
FLIPHAT addresses joint differential privacy for high-dimensional sparse linear bandits.
problem Efficient sequential decision-making with high-dimensional sparse features and privacy concerns.
method FLIPHAT combines iterative forgetting and N-IHT for sparse linear regression, achieving optimal regret.
result FLIPHAT achieves optimal regret in terms of privacy parameters, context dimension, and time horizon.
Thompson Sampling remains differentially private with minimal modifications.
problem Ensuring privacy in Thompson Sampling for multi-arm bandits.
method Demonstrated differential privacy of original Thompson Sampling, provided per-round guarantees, and introduced modifications for tighter privacy.
result Privacy guarantees can be tuned by modifying the algorithm, and these modifications impact expected regret.
We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round. When pulled, the arm receives some private reward v a v_a v a and can choose an amount x a x_a x a to pass on to the principal (keeping v a − x a v_a-x_a v a − x a for itself). All non-pulle…
Study non-stationary online auctions with semi-bandit feedback.
problem Maximize revenue in a non-stationary online second price auction.
method Develops an algorithm to handle non-stationary private value distributions.
result Achieves nearly optimal non-stationary regret bound.
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal O ~ ( T ) \tilde{O}(\sqrt{T}) O ~ ( T ) regret bounds. In the full-information setting, our results demonstrate that ε ε ε -differential privacy may be ensured for free -- in particular, the reg…
The paper studies MAB problems with LDP to balance privacy and service quality.
problem Balancing privacy and service quality in multi-armed bandit systems.
method Investigates regret minimization for MAB with LDP guarantee, proving lower bounds and proposing matching upper bounds algorithms.
result Regret upper bounds match lower bounds up to constant factors for MAB algorithms with LDP guarantee.
Paper addresses robust federated linear bandits against Byzantine attacks.
problem Byzantine attacks on a small fraction of agents in federated learning.
method Proposes a geometric median-based robust aggregation oracle.
result Achieves sublinear regret bound of i l d e O ( T 3 / 4 ) ilde{\mathcal{O}}({T^{3/4}}) i l d e O ( T 3/4 ) robust to fewer than half Byzantine agents. New algorithms protect user data while optimizing personalized decisions.
problem Personalized decision-making with private user data.
method Developed LDP algorithms for stochastic generalized linear bandits using SGD and OLS.
result Achieved the same regret bound as non-privacy settings with LDP.
DP-NCB algorithm ensures privacy and fairness in bandit decisions.
problem Achieving both privacy and fairness in bandit algorithms.
method Differentially Private Nash Confidence Bound (DP-NCB) framework.
result DP-NCB achieves optimal Nash regret while maintaining privacy.
This work improves privacy in federated combinatorial bandits by balancing regret and privacy.
problem Privacy-preserving learning in competitive online learning settings with quality constraints.
method Proposes P-FCB algorithm for federated combinatorial bandits, balancing regret and privacy.
result Improves regret while maintaining quality constraints and privacy guarantees.
Motivated by posted price auctions where buyers are grouped in an unknown number of latent types characterized by their private values for the good on sale, we investigate revenue maximization in stochastic dynamic pricing when the distribution of buyers' private values is supported on an unknown set of points in [0,1]…
New algorithm learns optimal policies in strategic MDPs with private types.
problem Optimal policy learning in strategic MDPs with private types and information asymmetry.
method PLAN algorithm using instrumental variable regression and pessimism principle.
result PLAN achieves near-optimal policy with 1 / K 1 / \sqrt{K} 1/ K optimality. BRACE addresses noncompliance in bandits, offering methods for recommendation and treatment policies.
problem Noncompliance in bandit problems complicates learning objectives and treatment effects.
method BRACE formalizes objective-choice, identifies direct-control regimes, and proposes a phase-doubling algorithm for IV inversion.
result BRACE delivers valid policy values and structural uncertainty, even under weak identification and homogeneity failure.
This paper studies trade-offs in private prediction methods.
problem Leakage of training data information in machine learning predictions.
method Private training and private prediction methods with trade-offs.
result Private training methods outperform private prediction methods in various settings.
Private method measures nonlinear correlations between data hosted across two entities.
problem Measuring nonlinear correlations between sensitive data hosted across multiple parties while preserving privacy.
method Differentially private estimator of distance correlation.
result First private estimator of nonlinear correlations in a multi-party setup.
New algorithms for privately learning decision lists and halfspaces.
problem Private learning of decision lists and halfspaces.
method Differentially private algorithms for PAC and online models.
result Private algorithms match or surpass non-private guarantees.
Private PGB boosts synthetic data quality using GANs and privacy techniques.
problem Differentially private GANs struggle with convergence and poor output quality.
method Combines reweighted samples from GAN training using Private Multiplicative Weights method.
result Improves synthetic data quality across various datasets and tasks.
Near-optimal private tests for simple and MLR hypotheses developed under Gaussian differential privacy.
problem Developing private tests for simple and MLR hypotheses under Gaussian differential privacy.
method A private mean estimator with data-driven clamping bounds, constructing private test statistics.
result Private tests achieve the same asymptotic relative efficiency as non-private most powerful tests.
PEARL uses AI to replicate private equity performance with liquid assets.
problem Lack of access to private equity due to high costs and complexity.
method Combines AI with liquid assets, incorporating asymmetry for better performance.
result Model outperforms liquid proxies and aligns with private equity benchmarks.