Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.
problem Maximizing reward by choosing actions sequentially from a set of experts.
method Proposed a variant of Exp4.P for infinitely many experts and a meta-algorithm.
result Proved high-probability upper bound of i l d e O ( i ∗ K + K T ) ilde{\mathcal{O}} \big( i^*K + \sqrt{KT} \big) i l d e O ( i ∗ K + K T ) on regret. New algorithm reduces regret in collaborative multi-agent bandit problems.
problem Optimizing decisions in a network of agents with communication delays.
method Follow-the-Regularized-Leader (FTRL) algorithm with suitable regularizers and communication protocols.
result Upper bound on individual regret matches lower bound up to a constant factor.
We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms that guarantee for each agent v v v an individual expected regret of $\widetilde{O}\left(\sqrt{\left(…
Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of band…
We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent impossibility result, we show how this can be made possible under certain mild addition…
A version of indifference valuation of a European call option is proposed that includes statistical regularities of nonstochastic randomness. Classical relations (forward contract value and Black-Scholes formula) are obtained as particular cases. We show that in the general case of nonstochastic randomness the minimal …
We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action p…
ABoB optimizes online configuration tuning by clustering parameters and accelerating learning.
problem Online optimization in large, dynamic parameter spaces.
method Hierarchical adversarial bandit framework.
result Significant performance gains in adversarial metric scenarios.
Efficient algorithm controls unknown systems with adversarial perturbations.
problem Controlling unknown linear systems with adversarial perturbations and convex losses.
method Measures regret against an optimal linear policy, provides efficient algorithm with sublinear regret bound.
result First efficient algorithm with sublinear regret bound of T^{2/3}.
New control methods for systems with adversarial perturbations.
problem Control systems with adversarial noise.
method Online convex optimization and convex relaxations.
result Low regret policies against adversarial perturbations.
We investigate multiarmed bandits with delayed feedback, where the delays need neither be identical nor bounded. We first prove that "delayed" Exp3 achieves the O ( ( K T + D ) ln K ) O(\sqrt{(KT + D)\ln K} ) O ( ( K T + D ) ln K ) regret bound conjectured by Cesa-Bianchi et al. [2019] in the case of variable, but bounded delays. Here, K K K is the number of actio…
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]…
Continuous-time SGD converges under certain conditions, useful for deep learning.
problem Minimizing population expected loss in learning problems.
method Continuous-time approximation of stochastic gradient descent.
result Establishes sufficient conditions for convergence, applicable to overparametrized neural networks.
Efficiently controls unknown linear systems with black-box interactions.
problem Controlling an unknown linear dynamical system from black-box interactions.
method First efficient algorithm with sublinear regret, using robust system identification.
result Resolves open problem on stochastic LQR and black-box LQR control.
A method to minimize regret in multi-agent control systems with adversarial disturbances.
problem Optimal control of dynamical systems with adversarial disturbances and multiple agents.
method Reduction from online convex optimization to a distributed algorithm for multi-agent control.
result The resulting distributed algorithm has low regret relative to the optimal precomputed joint policy.
Training avoids edge of stability by aligning Jacobian matrices.
problem Training neural networks on the edge of stability causes inaccuracies.
method Used an exponential Euler solver to prevent entering the edge of stability.
result Alignment of Jacobian matrices causes sharpness increase in Hessian.
Optimal algorithm for LQR control with improved regret bound.
problem Nonstochastic control with quadratic losses (LQR control).
method Online algorithm with optimal dynamic regret of i l d e O ( e x t m a x { n 1 / 3 T V ( M 1 : n ) 2 / 3 , 1 } ) ilde{O}( ext{max}\{n^{1/3} \mathcal{TV}(M_{1:n})^{2/3}, 1\}) i l d e O ( e x t ma x { n 1/3 TV ( M 1 : n ) 2/3 , 1 }) . result Improves the best known rate of i l d e O ( n ( T V ( M 1 : n ) + 1 ) ) ilde{O}(\sqrt{n (\mathcal{TV}(M_{1:n})+1)} ) i l d e O ( n ( TV ( M 1 : n ) + 1 ) ) for general convex losses. New algorithms tackle RKHS bandits with reduced complexity and improved performance.
problem Adversarial and stochastic RKHS bandit problems with high computational complexity.
method Combining approximation theory with misspecified linear bandit methods.
result First general algorithm for adversarial RKHS bandit problem.
Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
Paper solves stochastic contextual linear bandits using linear bandit algorithms.
problem Stochastic contextual linear bandits with unknown context distribution.
method Establishes a reduction framework to convert to linear bandit problems.
result Achieves nearly optimal regret bound of O ( d T log T ) O(d\sqrt{T\log T}) O ( d T log T ) . 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.
Graph-Triggered Bandits unify rested and restless bandits with graph-defined arm interactions.
problem Modeling sequential decision-making problems with evolving arm rewards.
method Graph-Triggered Bandits (GTBs) framework that generalizes rested and restless bandits using a graph.
result Rested and restless bandits are special cases of GTBs for suitable graphs.
New definition resolves ambiguity in non-stationary bandit classification.
problem Ambiguity in classifying non-stationary bandits using existing definitions.
method Introducing a formal definition that resolves ambiguity and provides a unified approach.
result Unified approach applicable to both Bayesian and frequentist formulations, resolves classification issues.
Unified approach for non-stationary and clustered bandits.
problem Solving non-stationary and clustered bandits with overlapping solutions.
method Test of homogeneity for seamless integration of non-stationary and clustered bandits.
result Unified solution framework for change detection and cluster identification.
A framework for auto-tuning hyper-parameters in contextual bandit algorithms.
problem Auto-tuning hyper-parameters in real-time for contextual bandit algorithms.
method Proposes a Syndicated Bandits framework to learn multiple hyper-parameters dynamically.
result Achieves optimal regret bounds under certain scenarios and handles multiple contextual bandit algorithms.
Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning algorithms may hijack their behavior, causing catastrophic loss in real-world appli…
New algorithm learns optimal exploration parameters for contextual bandits.
problem Learning optimal exploration in contextual bandits.
method Proposes two algorithms that learn optimal exploration parameters online based on context and reward.
result Demonstrates improved performance in learning optimal exploration compared to traditional methods.
Investigates sequential problems on graph structures and large action spaces.
problem Sequential decision-making on graph structures and large action spaces.
method Spectral bandits, side observations, influence maximization, kernel bandits, polymatroid bandits, function optimization, infinitely many-arms bandits.
result Contributions to graph and structured bandits.
Study on indexability of restless multi-armed bandits and rollout policy performance.
problem Maximizing discounted rewards in finite state restless multi-armed bandit problems.
method Decouple the problem into single-armed restless bandits, analyze using value iteration, and compare with Whittle index policy.
result Demonstrates conditions for indexability and compares performance of index policy and rollout policy.
New insights into multi-armed bandits with budget constraints.
problem Multi-armed bandits with supply/budget constraints.
method Characterization of logarithmic regret rates, simple regret, and reduction to other bandit problems.
result Full characterization of logarithmic, instance-dependent regret rates for BwK.
Optimal algorithm for identifying best arm in stochastic linear bandits with fixed confidence.
problem Identifying the best arm in stochastic linear bandits with fixed confidence.
method Extending an algorithm designed for Best Arm Identification to the ε ε ε -Thresholding Bandit Problem (TBP). result Asymptotically optimal algorithm for TBP.
A meta-UCB method combines stochastic bandit algorithms.
problem Combining multiple stochastic bandit algorithms efficiently.
method Meta-UCB procedure solving an N-armed bandit problem.
result Final regret depends only on the best base algorithm's regret.
New method for contextual bandits with corrupted context.
problem Contextual bandits with corrupted context in online settings.
method Combining contextual bandit and multi-armed bandit approaches.
result Improved learning from all iterations, including corrupted ones.
A new framework for structured bandits using influence diagrams and variational Thompson sampling.
problem Complex statistical dependencies in structured bandit problems.
method Influence diagram framework, variational Thompson sampling, tracking structured posterior distribution.
result Empirically evaluated algorithms perform as well as or better than existing baselines.
New algorithm for nonstationary multi-armed bandits with optimal performance.
problem Nonstationary multi-armed bandits with changing model parameters over time.
method Adaptive Resetting Bandit (ADR-bandit) algorithm using adaptive windowing techniques.
result ADR-bandit achieves nearly optimal performance in both abrupt and gradual changes.
First robust bandit algorithm for contextual bandits with sub-linear regret.
problem Vulnerability of linear contextual bandit algorithms to adversarial attacks.
method Proposes a robust bandit algorithm for stochastic linear contextual bandits under fully adaptive and omniscient attacks.
result Sub-linear regret under various attacks without requiring attack information.
Unified framework for high-dimensional bandit problems with low-dimensional structures.
problem Stochastic high-dimensional bandit problems with low-dimensional structures.
method Proposed a simple unified algorithm and a general analysis framework for the regret upper bound.
result Unified algorithm achieves comparable regret bounds in various high-dimensional bandit problems.
Survey and compare PAC-Bayes bounds for bandit problems.
problem Designing and evaluating bandit algorithms with strong performance guarantees.
method PAC-Bayes bounds applied to bandit problems.
result PAC-Bayes bounds useful for offline bandit algorithms, but loose for online algorithms.
New algorithms reduce regret for convex bandits with small comparator norms.
problem Optimizing in bandit convex optimization with varying comparator norms.
method Developed algorithms using techniques from full-information setting and new gradient estimators.
result Regret bounds are small when comparator norm is small.
Paper tackles domain adaptation for contextual bandits with sub-linear regret.
problem Adapting contextual bandit algorithms across domains with distribution shift.
method Learn a bandit model for the target domain using feedback from the source domain.
result Sub-linear regret bound maintained across domains.
New model tackles causal bandits with dependent variables.
problem Understanding reward-maximizing interventions in causal networks with dependent variables.
method Introduces hierarchical causal bandit model with a contextual variable capturing interactions among variables.
result Derives nearly matching regret bounds for binary context in causal bandits with dependent arms.
We consider the problem of best arm identification in a variant of multi-armed bandits called linked bandits. In a single interaction with linked bandits, multiple arms are played sequentially until one of them receives a positive reward. Since each interaction provides feedback about more than one arm, the sample comp…
New dynamic allocation methods for multi-armed bandit models.
problem Dynamic allocation problems in multi-armed bandit models.
method New types of dynamic allocation problems and proofs for Gittins index decomposition.
result New proofs for Gittins index decomposition and related results.
The paper tackles lifelong learning in multi-armed bandits, aiming to minimize average regret over multiple tasks.
problem Minimizing average regret in multi-armed bandits over multiple tasks.
method Confidence interval tuning of UCB algorithms and greedy algorithms applied to a bandit over bandit approach.
result Empirical improvement over previous work in the mortal bandit problem.
New algorithm for partially observable contexts in finance.
problem Decision making based on partially observable, correlated market information.
method EMKF-Bandit algorithm integrating system identification, filtering, and bandit algorithms.
result Sub-linear regret under conditions on filtering.
New meta-learning approach for bandit policies that achieve high average reward.
problem Designing bandit policies that balance between worst-case and Bayesian assumptions.
method Differentiable parameterized policies optimized using policy gradients.
result Proposed algorithm achieves low regret and is practical for various bandit problems.
A new algorithm reduces regret in cooperative multi-agent bandits with heavy-tailed data.
problem Cooperative multi-agent bandits with heavy-tailed data.
method MP-UCB algorithm incorporating robust estimation with message-passing protocol.
result Optimal regret bounds for MP-UCB in various settings.
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.