On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “private bandits”

Faster Rates for Private Adversarial Banditscs.LG

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.

differential privacy adversarial bandits expert advice regret bounds sublinear

2025-05-27abs ↗pdf ↗

Differentially-Private Federated Linear Banditscs.LG

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.

differentially-private federated learning bandits multi-agent cooperative learning

2020-10-22abs ↗pdf ↗

Locally Differentially Private (Contextual) Bandits Learningcs.LG

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.

Locally Differential Privacy Bandits Learning Contextual Bandits Privacy Guarantees Sub-linear Regret

2020-06-01abs ↗pdf ↗

No-Regret Algorithms for Private Gaussian Process Bandit Optimizationstat.ML

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.

private gaussian process bandit optimization differential privacy no-regret algorithms quadrature Fourier features

2021-02-24abs ↗pdf ↗

On the Optimal Regret of Locally Private Linear Contextual Banditstat.ML

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

ilde O(\sqrt{T})

regret upper bound for locally private linear contextual bandit.

locally private linear contextual bandit regret bounds mean absolute deviation principal component regression

2024-04-15abs ↗pdf ↗

On Private and Robust Banditscs.LG

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.

private bandits robust multi-armed bandits Huber's contamination differential privacy mean estimation

2023-02-06abs ↗pdf ↗

Shuffle and Joint Differential Privacy for Generalized Linear Contextual Banditsstat.ML

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

\sqrt{d/\varepsilon}

and

\sqrt{d/\varepsilon}

respectively.

differential privacy contextual bandits generalized linear models private convex optimization shuffle differential privacy

2026-01-31abs ↗pdf ↗

Differentially Private High Dimensional Banditscs.LG

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.

differential privacy high-dimensional bandits sparse parameters LASSO privacy-preserving algorithms

2024-02-06abs ↗pdf ↗

Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Schemestat.ML

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.

quantile multi-armed bandits best-arm identification successive elimination differential privacy sample complexity

2020-06-11abs ↗pdf ↗

Differentially Private Contextual Linear Banditscs.LG

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…

2018-09-28abs ↗pdf ↗

Robust and differentially private stochastic linear banditscs.LG

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.

stochastic linear bandits differential privacy robustness local differential privacy adversarial robustness

2023-04-23abs ↗pdf ↗

Differential Privacy in Kernelized Contextual Bandits via Random Projectionsstat.ML

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.

Differential Privacy Kernelized Contextual Bandits Random Projections Cumulative Regret Privacy Parameter

2025-07-18abs ↗pdf ↗

Algorithms for Differentially Private Multi-Armed Banditsstat.ML

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…

2015-11-27abs ↗pdf ↗

Dynamic Global Sensitivity for Differentially Private Contextual Banditscs.LG

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)

-differential privacy with reduced noise and improved regret.

differential privacy contextual bandits dynamic global sensitivity regret analysis noise injection

2022-08-30abs ↗pdf ↗

Private and Byzantine-Proof Cooperative Decision-Makingstat.ML

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.

cooperative decision-making privacy byzantine agents stochastic bandit upper-confidence bound

2022-05-27abs ↗pdf ↗

Mitigating Bias in Adaptive Data Gathering via Differential Privacycs.LG

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…

2018-06-06abs ↗pdf ↗

On Private Online Convex Optimization: Optimal Algorithms in

\ell_p

-Geometry and High Dimensional Contextual Banditscs.LG

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\leq 2

and state-of-the-art excess risk for

2<p\leq\infty

private online optimization Frank-Wolfe algorithm recursive gradients differential privacy streaming data

2022-06-16abs ↗pdf ↗

Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regressioncs.LG

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.

private linear regression covariate distribution minimax rates L1 analogues regret bounds

2025-02-18abs ↗pdf ↗

AdaPrivate-TS: Private Thompson Sampling for Contextual Bandits with Privacy Amplificationcs.LG

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

differential privacy contextual bandits Thompson Sampling privacy amplification

2026-06-19abs ↗pdf ↗

Locally Private Nonparametric Contextual Multi-armed Banditsstat.ML

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.

local differential privacy nonparametric bandits minimax optimality jump-start scheme covariate shift

2025-03-11abs ↗pdf ↗

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Banditscs.LG

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

-global DP extensions of UCB and KL-UCB algorithms.

result AdaP-KLUCB algorithm achieves optimal regret bound under

ε

-global DP constraints.

Differential Privacy Multi-Armed Bandits Partial Information Regret Minimization Privacy Constraints

2022-09-06abs ↗pdf ↗

Privacy-Preserving Banditscs.LG

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…

2019-09-10abs ↗pdf ↗

Concentrated Differential Privacy for Banditsstat.ML

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.

Differential Privacy Bandits Concentrated Differential Privacy Recommender Systems Privacy

2023-09-01abs ↗pdf ↗

(Locally) Differentially Private Combinatorial Semi-Banditscs.LG

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.

Privacy Combinatorial Semi-Bandits Differential Privacy Local Differential Privacy Regret Bounds

2020-06-01abs ↗pdf ↗

Privacy-Preserving Multi-Party Contextual Banditscs.LG

Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…

2019-10-11abs ↗pdf ↗

Differentially Private Online Submodular Optimizationcs.DS

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 $T$ submodular functions over a collection of $n$ elements arrive online, and at each timestep the algorithm must choose a subset of $[n]…

2018-07-06abs ↗pdf ↗

A Bandit Model for Human-Machine Decision Making with Private Information and Opacitycs.LG

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.

bandit model human-machine decision making private information opacity optimization

2020-07-09abs ↗pdf ↗

Differentially Private Kernelized Contextual Banditsstat.ML

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

queries.

differential privacy kernelized bandits contextual bandits privacy parameter reproducing kernel Hilbert space

2025-01-13abs ↗pdf ↗

An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rulestat.ML

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 $Ω\left(\frac{K\log(T)}ε \right)$ [Shar…

2019-05-22abs ↗pdf ↗

FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Banditsstat.ML

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.

differential privacy sparse linear bandits high dimensional data regret minimization privacy-preserving algorithms

2024-05-22abs ↗pdf ↗

Thompson Sampling Itself is Differentially Privatecs.LG

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.

Thompson Sampling Differential Privacy Multi-Arm Bandits Regret Analysis Privacy Guarantees

2024-07-20abs ↗pdf ↗

Multi-armed Bandit Problems with Strategic Armscs.GT

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 $v_a$ and can choose an amount $x_a$ to pass on to the principal (keeping $v_a-x_a$ for itself). All non-pulle…

2017-06-27abs ↗pdf ↗

The Price of Differential Privacy For Online Learningcs.LG

We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal $\tilde{O}(\sqrt{T})$ regret bounds. In the full-information setting, our results demonstrate that $ε$ -differential privacy may be ensured for free -- in particular, the reg…

2017-01-27abs ↗pdf ↗

Multi-Armed Bandits with Local Differential Privacycs.LG

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.

multi-armed bandits local differential privacy regret minimization stochastic bandit privacy

2020-07-06abs ↗pdf ↗

Byzantine-Robust Federated Linear Banditscs.LG

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

ilde{\mathcal{O}}({T^{3/4}})

robust to fewer than half Byzantine agents.

federated learning linear bandits Byzantine attacks robust aggregation geometric median

2022-04-03abs ↗pdf ↗

Generalized Linear Bandits with Local Differential Privacystat.ML

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.

local differential privacy contextual bandits stochastic gradient descent ordinary least squares personalized decision-making

2021-06-07abs ↗pdf ↗

DP-NCB: Privacy Preserving Fair Banditscs.LG

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.

Privacy Preserving Fairness Bandits Differential Privacy Nash Regret

2025-08-05abs ↗pdf ↗

Differentially Private Federated Combinatorial Bandits with Constraintscs.LG

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.

differential privacy federated learning combinatorial bandits regret minimization competitive learning

2022-06-27abs ↗pdf ↗

Dynamic Pricing with Finitely Many Unknown Valuationscs.LG

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]…

2018-07-09abs ↗pdf ↗

Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentsstat.ML

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 / \sqrt{K}

optimality.

reinforcement learning strategic decision-making information asymmetry instrumental variables myopic agents

2022-08-23abs ↗pdf ↗

What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effectsstat.ML

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.

noncompliance bandits recommendation welfare treatment learning IV inference

2026-03-10abs ↗pdf ↗

Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Settingcs.LG

In this paper, we study the non-stationary online second price auction problem. We assume that the seller is selling the same type of items in $T$ rounds by the second price auction, and she can set the reserve price in each round. In each round, the bidders draw their private values from a joint distribution unknown t…

2019-11-14abs ↗pdf ↗

The Trade-Offs of Private Predictioncs.LG

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 prediction machine learning privacy trade-offs training methods

2020-07-09abs ↗pdf ↗

Private measurement of nonlinear correlations between data hosted across multiple partiescs.LG

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.

differential privacy nonlinear correlations distance correlation multi-party private feature screening

2021-10-19abs ↗pdf ↗

Privately Learning Decision Lists and a Differentially Private Winnowcs.LG

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.

differential privacy private learning decision lists halfspaces Winnow algorithm

2026-02-07abs ↗pdf ↗

Private Post-GAN Boostingcs.LG

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.

Differential Privacy GANs Post-GAN Boosting Private Multiplicative Weights Synthetic Data

2020-07-23abs ↗pdf ↗

Near-Optimal Private Tests for Simple and MLR Hypothesesstat.ML

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.

private testing Gaussian differential privacy simple hypotheses MLR hypotheses monotone likelihood ratio

2026-01-29abs ↗pdf ↗

PEARL: Private Equity Accessibility Reimagined with Liquidityq-fin.TR

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.

Private Equity Accessibility Liquidity AI Performance

2025-10-27abs ↗pdf ↗