We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed solely for one of the regimes are known to be sub-optimal for the alternate regime…
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
48 results for “contextual multi-armed bandits”
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.
Paper tackles transfer learning for contextual multi-armed bandits under covariate shift.
problem Nonparametric contextual multi-armed bandits with covariate shift.
method Established minimax rate of convergence, proposed transfer learning algorithm.
result Achieved near-optimal statistical guarantees for learning in target domain.
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.
Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven (principled) exploration, or non-linearly, by using epsilon-greedy exploration policies. Here we present a deep learning framework for cont…
New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.
problem Improving Thompson Sampling for partially observed context bandits.
method Proposed a Thompson Sampling algorithm for partially observable contextual multi-armed bandits with theoretical performance guarantees.
result Regret scales logarithmically with time and the number of arms, and linearly with the dimension.
Improved -greedy handles strategic bidding in PPC auctions.
problem Strategic bidding in PPC auctions with personalization and corruptions.
method Extended -greedy to handle strategic arms in contextual multi-arm bandit.
result -greedy is robust to adversarial corruptions and degrades linearly with corruption.
The paper tackles carousel personalization in music streaming apps using contextual bandits.
problem Selecting relevant items to display in carousels for personalized content recommendation.
method Modeling carousel personalization as a contextual multi-armed bandit problem with multiple plays, cascade-based updates and delayed batch feedback.
result Empirically shows the effectiveness of the framework in capturing characteristics of real-world carousels.
This work explores the idea of a causal contextual multi-armed bandit approach to automated marketing, where we estimate and optimize the causal (incremental) effects. Focusing on causal effect leads to better return on investment (ROI) by targeting only the persuadable customers who wouldn't have taken the action orga…
This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these adaptations are achieved through bootstrapping or approximate bootstrapping, whil…
New method for contextual bandit with missing rewards.
problem Contextual bandit with missing rewards in online settings.
method Combining contextual bandit approach with unsupervised learning (clustering) to estimate missing rewards.
result Promising empirical results on real-life datasets.
The paper tackles risk-averse multi-armed bandit with linear payoffs.
problem Risk-averse contextual multi-armed bandit problem with linear payoffs.
method Apply Thompson Sampling algorithm for disjoint model and provide comprehensive regret analysis.
result Proved an regret bound for mean-variance criterion.
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.
We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommende…
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.
We study a multi-armed bandit problem with covariates in a setting where there is a possible delay in observing the rewards. Under some mild assumptions on the probability distributions for the delays and using an appropriate randomization to select the arms, the proposed strategy is shown to be strongly consistent.
Over the past decade, contextual bandit algorithms have been gaining in popularity due to their effectiveness and flexibility in solving sequential decision problems---from online advertising and finance to clinical trial design and personalized medicine. At the same time, there are, as of yet, surprisingly few options…
Study sparsity benefits in infinite feature contextual bandits.
problem Minimizing regret in infinite feature contextual bandits.
method Novel reduction to multi-armed bandits, Feel-Good Thompson Sampling algorithm.
result Regret bounds match lower bounds up to logarithmic factors, logarithmic dependence on effective features.
Fairness in AI decisions for users with varying performance.
problem Ensuring fairness in AI decisions for users with different performance levels.
method Contextual Multi-Armed Bandit algorithm with fairness constraints.
result Accounting for user contexts improves fairness in AI decisions.
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better empirical performance compared to the state-of-the-art methods. However, many ques…
Contextual bandits have the same exploration-exploitation trade-off as standard multi-armed bandits. On adding positive externalities that decay with time, this problem becomes much more difficult as wrong decisions at the start are hard to recover from. We explore existing policies in this setting and highlight their …
New framework uses tree ensembles for contextual bandits.
problem Optimizing decisions in dynamic environments with contextual information.
method Adapts Upper Confidence Bound and Thompson Sampling to tree ensemble methods.
result Tree ensemble methods outperform traditional methods in regret minimization and runtime.
In recent years, multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance, due to its stellar performance combined with certain attractive properties, such as learning from less feedback. The multi-armed ban…
An algorithm for maximizing rewards under linear cost constraints.
problem Maximizing rewards while adhering to cost constraints in a linear bandit problem.
method Proposes an upper-confidence bound algorithm called optimistic pessimistic linear bandit (OPLB) for constrained contextual linear bandits.
result Proves an bound on regret for the proposed algorithm.
Contextual multi-armed bandit (MAB) algorithms have been shown promising for maximizing cumulative rewards in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. However, most of the proposed contextual MAB algorithms assume linear relationships be…
Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We study a consideration for the expl…
Cramming method evaluates learned policies from contextual bandits efficiently.
problem Evaluating final learned policies from contextual bandit algorithms.
method On-policy evaluation using a single pass of data, ensuring consistency and asymptotic normality.
result Cramming method reduces evaluation standard error by approximately 40% compared to off-policy methods.
Novel algorithm reduces feature inclusion in online decision-making.
problem Optimizing decision-making for personalized user experiences with fairness.
method Online Batched Sequential Inclusion (OBSI) algorithm for sequential feature inclusion.
result OBSI outperforms other algorithms in terms of regret, relevance of features, and compute.
New algorithm for traffic routing in congested conditions.
problem Optimal routing in congested traffic networks.
method Congested Bandits model, UCB algorithm, iterative least squares planner.
result No-regret algorithms for congestion-aware routing.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
Neural Thompson Sampling uses deep neural networks for contextual bandit problems.
problem Solving contextual multi-armed bandit problems.
method Adapts deep neural networks for exploration and exploitation in a novel posterior distribution.
result Guaranteed cumulative regret of for bounded reward functions.
A new algorithm for contextual combinatorial bandits reduces regret.
problem Balancing exploration and exploitation in sequential decisions with risk sensitivity.
method Contextual combinatorial conservative bandits framework, with algorithms and regret bounds proven.
result Proven regret bound of for known conservative reward, and unknown reward case.
Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placement, and other applications. In this work, we propose a multi-task learning frame…
New algorithms for model selection in linear contextual bandits without feature diversity conditions.
problem Model selection in linear contextual bandits without feature diversity conditions.
method Data-adaptive algorithms that provide model selection guarantees without feature diversity conditions.
result O(d^α T^{1-α}) model selection guarantees with no feature diversity conditions.
Modified Meta-TS for linear contextual bandits reduces regret.
problem Optimizing decision-making in dynamic environments with context vectors.
method Meta-TSLB algorithm for linear contextual bandits, analyzing Bayes regret.
result Derives an bound on Bayes regret.
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…
New acquisition function for extreme rewards in bandits.
problem Online decision making with extreme payoffs in multi-armed bandits.
method Modeling payoffs as Gaussian processes and using a novel UCB acquisition function.
result Demonstrated benefits across synthetic and real-world benchmarks.
In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously learning how the world operates, is the multi-armed bandit setting and, in particular,…
We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model of rewards and establish a minimax lower bound on the mean squared error (MSE).…
New findings on universal learning in contextual bandits with adversarial rewards.
problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.
There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…
New algorithms improve contextual bandit performance by adapting to problem difficulty.
problem Improving contextual bandit performance on problems with varying difficulty.
method Introducing complexity measures and oracle-efficient algorithms.
result Achieves optimal instance-dependent regret bounds for rich policy classes.
Improved control approach for correlated bandits with better performance.
problem General multi-armed bandit problem with correlated elements.
method Introducing entropy regularisation to obtain a smooth asymptotic approximation of the value function, leading to a semi-index approximation of the optimal decision process.
result Performance of Asymptotic Randomised Control (ARC) algorithm compares favorably with other approaches.
We analyze the -armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of , where is the context dimension, f…
Many efficient algorithms with strong theoretical guarantees have been proposed for the contextual multi-armed bandit problem. However, applying these algorithms in practice can be difficult because they require domain expertise to build appropriate features and to tune their parameters. We propose a new method for the…
Proposes EE-Net for neural exploration in contextual bandits.
problem Exploitation-Exploration tradeoff in contextual bandits.
method Uses two neural networks: Exploitation and Exploration, to learn reward function and adaptively explore.
result Achieves regret and outperforms existing methods.
We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline policy which is known to perform well on the task. To tackle this problem we use a nonparametric model and propose an algorithm splitting t…
New principle optimizes bandit decisions with context.
problem Dealing with general function classes and large context spaces in bandits.
method Upper Counterfactual Confidence Bounds (UCCB) principle.
result Proves optimality and efficiency in complex settings.