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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “causal bandit”

Causal Bandits with Unknown Graph Structurestat.ML

New algorithms for causal bandits without knowing the graph structure.

problem Causal bandit problems with unknown graph structure.

method Developed novel causal bandit algorithms for causal trees, forests, and general graphs without prior knowledge of the causal graph.

result Regret guarantees significantly improved over standard MAB algorithms under mild conditions.

Causal Bandits Unknown Graph Structure Regret Guarantees Causal Trees Causal Forests

2021-06-05abs ↗pdf ↗

Chronological Causal Banditsstat.ML

Chronological Causal Bandits (CCB) tackles dynamic causal decision-making.

problem Dynamic causal decision-making in a system where rewards depend on past interventions.

method Introduces a new MAB problem (Chronological Causal Bandit) where rewards are influenced by a dynamic causal model.

result Early findings show the CCB can transfer information between sequential MABs.

chronological causal bandits dynamic causal model multi-armed bandit sequential decision-making causal effects

2021-12-03abs ↗pdf ↗

Hierarchical Causal Banditstat.ML

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.

causal bandit dependent variables regret bounds hierarchical model

2021-03-07abs ↗pdf ↗

The Minimal Search Space for Conditional Causal Banditscs.LG

This paper identifies the minimal set of nodes for optimal conditional interventions in causal bandits.

problem Optimizing decision-making in causal bandits with conditional interventions.

method Graphical characterization and efficient algorithm to identify the minimal set of nodes.

result The proposed algorithm significantly prunes the search space and accelerates convergence rates.

causal bandits conditional interventions graphical models multi-armed bandits optimal interventions

2025-02-10abs ↗pdf ↗

Causal Bandits with Propagating Inferencestat.ML

Bandit is a framework for designing sequential experiments. In each experiment, a learner selects an arm $A \in \mathcal{A}$ and obtains an observation corresponding to $A$ . Theoretically, the tight regret lower-bound for the general bandit is polynomial with respect to the number of arms $|\mathcal{A}|$ . This makes ba…

2018-06-06abs ↗pdf ↗

Causal Bandits: Learning Good Interventions via Causal Inferencestat.ML

We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm t…

2016-06-10abs ↗pdf ↗

On Transportability for Structural Causal Banditscs.LG

The paper explores how to apply causal knowledge across different datasets to improve learning.

problem How to apply causal knowledge across different datasets to improve learning.

method Investigates the structural causal bandit with transportability, fusing priors from source environments to enhance learning in the deployment setting.

result Achieves a sub-linear regret bound with an explicit dependence on informativeness of prior data, potentially outperforming standard bandit approaches.

transportability structural causal bandits learning regret bound invariances

2025-11-22abs ↗pdf ↗

Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approachcs.LG

The paper tackles bandit problems with biased offline data by using causal methods.

problem Improving bandit algorithms with biased offline data that includes confounding and selection biases.

method Formalizes the problem from a causal perspective, categorizes biases, and derives robust bounds for each arm.

result Causal bounds can guide the bandit agent to learn a nearly-optimal decision policy and consistently reduce asymptotic regret.

bandit algorithms biased offline data confounding bias selection bias causal approach

2023-12-20abs ↗pdf ↗

Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginalscs.LG

This work explores adaptive strategies for multi-armed bandits with causal structure, achieving optimal regret bounds.

problem Adapting to causal structure in multi-armed bandits with additional observed variables.

method Reduction to linear bandits and establishment of Pareto optimal frontier of adaptive rates.

result Established upper and lower bounds on adaptive rates, resolving open questions.

Causal Bandits Multi-Armed Bandits Conditional Benign Structure Pareto Optimal Frontier Regret Bounds

2024-07-01abs ↗pdf ↗

Contextual Multi-Armed Bandits for Causal Marketingcs.LG

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…

2018-10-02abs ↗pdf ↗

Partial Structure Discovery is Sufficient for No-regret Learning in Causal Banditsstat.ML

New algorithm learns causal graph to minimize regret in bandits without full structure.

problem Learning optimal decisions in bandits with unknown causal graph and latent confounders.

method Two-stage approach: first learns ancestors and necessary confounders, second applies standard bandit algorithm.

result No full causal structure needed for optimal decisions; only necessary confounders are crucial.

Causal Bandits No-regret Learning Latent Confounders Ancestral Graph Optimal Arms

2024-11-06abs ↗pdf ↗

Additive Causal Bandits with Unknown Graphcs.LG

New algorithm identifies best intervention without graph knowledge.

problem Finding best intervention in causal bandit setting with unknown graph.

method Additive combinatorial linear bandit problem with action-elimination algorithm.

result One can identify best intervention without explicitly learning graph parents.

causal bandits unknown graph additive assumption action-elimination sample complexity

2023-06-13abs ↗pdf ↗

Causal Bandits without Graph Learningstat.ML

New algorithm finds causal parent nodes without graph learning.

problem Finding causal relationships without knowing the graph structure.

method Developed an efficient algorithm using atomic interventions.

result Algorithm optimally performs interventions with sublinear complexity.

Causal Bandits Graph Learning Atomic Interventions Optimal Algorithm Sublinear Complexity

2023-01-26abs ↗pdf ↗

Combinatorial Causal Banditscs.LG

Algorithm BGLM-OFU minimizes regret in combinatorial causal bandits with binary models.

problem Minimizing expected regret in combinatorial causal bandits with binary generalized linear models.

method BGLM-OFU algorithm based on maximum likelihood estimation for Markovian BGLMs, and causal inference techniques for linear models with hidden variables.

result Achieves

O(\sqrt{T}\log T)

regret for binary generalized linear models.

combinatorial causal bandits binary generalized linear models maximum likelihood estimation regret analysis causal inference

2022-06-04abs ↗pdf ↗

Combinatorial Causal Bandits without Graph Skeletoncs.LG

New algorithm reduces regret in combinatorial causal bandits without graph structure.

problem Minimizing regret in combinatorial causal bandits without graph structure.

method Design of algorithms for binary general causal models and BGLMs without graph skeleton.

result Achieves

O(\sqrt{T}\ln T)

expected regret for causal models and

O(T^{\frac{2}{3}}\ln T)

for BGLMs.

combinatorial causal bandits regret minimization binary general causal models BGLMs graph structure

2023-01-31abs ↗pdf ↗

Adaptively Exploiting d-Separators with Causal Banditsstat.ML

Adaptive algorithm reduces regret in causal bandits.

problem Minimize regret in causal bandits with unknown d-separators.

method Adaptive algorithm exploiting d-separators without prior knowledge.

result Significantly smaller regret than previous methods.

causal bandits d-separators regret minimization adaptivity

2022-02-10abs ↗pdf ↗

Regret Analysis of Bandit Problems with Causal Background Knowledgestat.ML

We study how to learn optimal interventions sequentially given causal information represented as a causal graph along with associated conditional distributions. Causal modeling is useful in real world problems like online advertisement where complex causal mechanisms underlie the relationship between interventions and …

2019-10-11abs ↗pdf ↗

Invariant Policy Learning: A Causal Perspectivecs.LG

The paper tackles policy learning in dynamic environments using causal methods.

problem Existing reinforcement learning algorithms assume static mechanisms, but real-world systems often have changing mechanisms.

method The paper introduces multi-environment contextual bandits and policy invariance to handle environmental shifts.

result An optimal invariant policy is guaranteed to generalize across environments under suitable assumptions.

policy learning environmental shifts causality invariance contextual bandits

2021-06-01abs ↗pdf ↗

Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewardscs.LG

Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.

problem Nonstationary environment with changing base arms' distributions and causal relationships.

method Upper Confidence Bound (UCB) algorithm with change-point detector and group restart strategy.

result Regret upper bound reflecting effects of structural and distribution changes.

combinatorial semi-bandit piecewise stationarity causally related rewards change-point detection group restart

2023-07-26abs ↗pdf ↗

Causal Bandits for Linear Structural Equation Modelsstat.ML

The paper tackles causal bandits for SEMs, proposing algorithms that avoid estimating $2^N$ reward distributions.

problem Designing an optimal sequence of interventions in causal graphical models to minimize cumulative regret.

method Proposes two algorithms for causal bandits for linear structural equation models (SEMs), avoiding the estimation of

2^N

reward distributions.

result Cumulative regrets scale as

ilde{\cal O} (d^{L+\frac{1}{2}} \sqrt{NT})

under bounded noise and parameter space.

causal bandits linear structural equation models interventions cumulative regret regression

2022-08-26abs ↗pdf ↗

Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluationcs.LG

DFPV improves PCL for confounded bandit policy evaluation.

problem Estimating causal effects in confounded settings with high-dimensional data.

method Deep feature proxy variable method (DFPV) for high-dimensional, nonlinear relationships.

result DFPV outperforms state-of-the-art methods on synthetic benchmarks and confounded bandit problems.

proxy causal learning confounded bandit deep feature proxy off-policy evaluation high-dimensional data

2021-06-07abs ↗pdf ↗

Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewardscs.LG

A new algorithm tackles delayed combinatorial semi-bandit with causal relations.

problem Optimizing decisions in a non-stationary environment with delayed and causally related rewards.

method Formalized as a non-stationary delayed combinatorial semi-bandit problem, the approach models causal relations with a directed graph in a stationary structural equation model. The agent learns these relations from delayed feedback to optimize decisions.

result Proved a regret bound for the proposed algorithm's performance.

delayed combinatorial semi-bandit causal relations structural equation model regret bound feedback delay

2023-07-18abs ↗pdf ↗

A Correction of Pseudo Log-Likelihood Methodcs.LG

Corrects pseudo log-likelihood method issues in various applications.

problem Log-likelihood function unbounded issues in pseudo log-likelihood methods.

method Provided a counterexample and corrected algorithms in previous literature.

result Ensured well-definedness of maximum pseudo log-likelihood estimation.

pseudo log-likelihood maximum likelihood estimation contextual bandits influence maximization causal bandits

2024-03-26abs ↗pdf ↗

Causal Bandits with General Causal Models and Interventionsstat.ML

The paper tackles causal bandits with unknown SCMs and soft interventions, providing upper and lower bounds on regret.

problem Optimizing interventions in a causal system with unknown SCMs and soft interventions.

method Assumes unknown SCMs from a general class, allows infinite interventions, and provides upper and lower bounds on regret.

result General upper and lower bounds on cumulative achievable regret for various SCMs.

causal bandits general SCMs soft interventions regret bounds graph parameters

2024-03-01abs ↗pdf ↗

Improved Bound for Robust Causal Bandits with Linear Modelsstat.ML

New algorithm reduces regret in CBs with time-varying models.

problem Designing robust interventions in CBs with unknown, fluctuating causal models.

method Proposes a robust CB algorithm with upper and lower bounds on regret.

result Achieves nearly optimal

ilde{\mathcal{O}}(\sqrt{T})

regret under certain conditions.

Causal Bandits Temporal Model Fluctuations Linear Structural Equation Models Cumulative Regret Optimal Regret

2024-05-13abs ↗pdf ↗

Budgeted and Non-budgeted Causal Banditscs.LG

New algorithms for efficient causal interventions with budget constraints and without constraints.

problem Efficiently learning best interventions in causal graphs with budget constraints.

method Developed algorithms for both budgeted and non-budgeted causal bandits, optimizing regret and side-information usage.

result Proposed algorithms minimize cumulative regret and perform better than standard methods.

causal inference multi-armed bandits regret minimization budget constraints side-information

2020-12-13abs ↗pdf ↗

Active and Passive Causal Inference Learningcs.LG

Paper introduces active and passive causal inference techniques.

problem Causal inference in machine learning.

method Categorizes causal inference techniques into active and passive approaches.

result Describes and discusses various causal inference methods.

causal inference machine learning randomized controlled trials bandit-based approaches matching

2023-08-18abs ↗pdf ↗

Causal Predictive Optimization and Generation for Business AIcs.LG

New approach optimizes sales process for B2B businesses.

problem Optimizing the sales process for B2B businesses.

method Causal Predictive Optimization and Generation with three layers: prediction, optimization, and serving.

result Significant wins over legacy systems in LinkedIn implementation.

sales optimization business AI causal ML constraint optimization contextual bandit

2025-05-14abs ↗pdf ↗

Linear Causal Bandits: Unknown Graph and Soft Interventionsstat.ML

This paper tackles unknown causal graphs and soft interventions, establishing regret bounds and an efficient algorithm.

problem Designing causal bandit algorithms with unknown causal graphs and stochastic intervention models.

method Establishes novel regret bounds and presents a computationally efficient algorithm for unknown graph and soft interventions.

result Regret bounds for unknown graph and soft interventions, with a universal minimax lower bound.

causal bandits unknown graph soft interventions regret bounds minimax lower bound

2024-11-04abs ↗pdf ↗

Marginal Density Ratio for Off-Policy Evaluation in Contextual Banditsstat.ML

New estimator reduces variance in off-policy evaluation for contextual bandits.

problem High variance in current OPE methods for contextual bandits.

method Marginal Density Ratio (MR) estimator focusing on marginal distribution shift.

result MR estimator reduces variance compared to IPW and DR methods.

Off-Policy Evaluation Contextual Bandits Marginal Density Ratio Inverse Probability Weighting Doubly Robust

2023-12-03abs ↗pdf ↗

Robust Causal Bandits for Linear Modelsstat.ML

This paper addresses robust CBs for linear SEMs with model fluctuations.

problem Designing interventions in causal systems with linear SEMs that are robust to model fluctuations.

method Develops a robust CB algorithm and analyzes its regret under model deviation.

result The proposed algorithm achieves nearly optimal

ilde{\mathcal{O}}(\sqrt{T})

regret when

C

o(\sqrt{T})

and maintains sub-linear regret for a broader range of

C

causal bandits linear SEMs model fluctuations cumulative regret sub-linear regret

2023-10-30abs ↗pdf ↗

Balanced Linear Contextual Banditscs.LG

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 develop algorithms for contextual …

2018-12-15abs ↗pdf ↗

Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decisioncs.LG

A fundamental question for companies with large amount of logged data is: How to use such logged data together with incoming streaming data to make good decisions? Many companies currently make decisions via online A/B tests, but wrong decisions during testing hurt users' experiences and cause irreversible damage. A ty…

2020-01-16abs ↗pdf ↗

Contextual Bandits with Latent Confounders: An NMF Approachcs.LG

Motivated by online recommendation and advertising systems, we consider a causal model for stochastic contextual bandits with a latent low-dimensional confounder. In our model, there are $L$ observed contexts and $K$ arms of the bandit. The observed context influences the reward obtained through a latent confounder var…

2016-06-01abs ↗pdf ↗

A Two-armed Bandit Framework for A/B Testingstat.ML

Improves A/B testing power using a two-armed bandit framework.

problem Comparing outcomes under a new policy to a control.

method Doubly robust estimation, two-armed bandit framework, permutation-based method.

result Superior performance in A/B testing compared to existing methods.

A/B testing two-armed bandit doubly robust reinforcement learning permutation test

2025-07-24abs ↗pdf ↗

Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Makingcs.LG

Bridges uplift modeling and sequential decision-making with online budget allocation.

problem Treatment allocation under budget constraints in digital advertising.

method Budget-Constrained Causal Bandits (BCCB) integrates learning, exploration, and budget pacing.

result Data-efficiency crossover: BCCB operates effectively from the first user, 3-5x lower performance variance.

causal bandits budget constraints uplift modeling sequential decision-making online learning

2026-04-28abs ↗pdf ↗

Estimation Considerations in Contextual Banditsstat.ML

2017-11-19abs ↗pdf ↗

Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effectstat.ML

New algorithms improve estimation of treatment effects.

problem Estimating Average Treatment Effect (ATE) in adaptive settings.

method Optimistic algorithms for adaptive estimation using AIPW estimator.

result Significant theoretical and empirical gains over prior methods.

Average Treatment Effect Adaptive Estimation Optimism Augmented Inverse Probability Weighting Causal Inference

2025-02-07abs ↗pdf ↗

Causal Bayesian Optimization with Unknown Graphsstat.ML

Proposes a new CBO method without known causal graphs.

problem Optimizing outcomes with unknown causal graphs.

method New CBO method focusing on direct causal parents, learning Bayesian posterior over them.

result Empirical validation and competitive performance with GP approximation.

Causal Bayesian Optimization Unknown Graphs Direct Causal Parents Bayesian Posterior Gaussian Process

2025-03-25abs ↗pdf ↗

Scalable Policy Maximization Under Network Interferencestat.ML

New algorithm optimizes interventions under network interference, scaling to large networks.

problem Optimal policy learning under network interference where one individual's treatment affects others.

method Developed a scalable Thompson sampling algorithm for dynamic networks.

result Proved a Bayesian regret bound that is sublinear in network size and rounds.

Thompson Sampling Network Interference Causal Inference Bandit Algorithms Scalability

2025-05-23abs ↗pdf ↗

Uncertainty Quantification and Causal Considerations for Off-Policy Decision Makingstat.ML

New methods improve robust decision-making under uncertainty in off-policy evaluation.

problem Statistical uncertainty and causal considerations in off-policy evaluation.

method Marginal Ratio (MR) estimator, Conformal Off-Policy Prediction (COPP), causal bounds.

result Improved robustness and uncertainty quantification in off-policy decision-making.

off-policy evaluation uncertainty quantification causal inference contextual bandits digital twins

2025-02-09abs ↗pdf ↗

Rarely-switching linear bandits: optimization of causal effects for the real worldstat.ML

Excessively changing policies in many real world scenarios is difficult, unethical, or expensive. After all, doctor guidelines, tax codes, and price lists can only be reprinted so often. We may thus want to only change a policy when it is probable that the change is beneficial. In cases that a policy is a threshold on …

2019-05-30abs ↗pdf ↗

Instrument-Armed Banditsstat.ML

We extend the classic multi-armed bandit (MAB) model to the setting of noncompliance, where the arm pull is a mere instrument and the treatment applied may differ from it, which gives rise to the instrument-armed bandit (IAB) problem. The IAB setting is relevant whenever the experimental units are human since free will…

2017-05-21abs ↗pdf ↗

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observationscs.LG

A new algorithm CAP learns optimal policies from observational data with confounding bias and missing observations.

problem Offline contextual bandit with confounding bias and missing observations.

method CAP policy learning, forming reward function as solution of integral equation system, building confidence set, and greedily taking action with pessimism.

result Developed an upper bound to the suboptimality of CAP for the offline contextual bandit problem.

Contextual Bandit Confounding Bias Missing Observations Policy Learning Offline Reinforcement Learning

2023-03-20abs ↗pdf ↗

Fixed-Confidence Best-Arm Identification for Causal Mediation Analysisstat.ML

The paper identifies the best treatment to maximize NDPO, a key outcome in causal mediation analysis.

problem Identifying the treatment that maximizes the expected natural direct potential outcome (NDPO) in causal mediation analysis.

method Developed a fixed-confidence best-arm identification (BAI) algorithm based on the Track-and-Stop (TaS) framework, using a cutting-set method to solve a semi-infinite optimization problem.

result The proposed algorithm achieves sample-efficient identification with a high-probability correctness guarantee and asymptotic optimality.

causal mediation analysis natural direct potential outcome best-arm identification fixed-confidence cutting-set method

2026-07-05abs ↗pdf ↗

AutoML for Contextual Banditscs.LG

Contextual Bandits is one of the widely popular techniques used in applications such as personalization, recommendation systems, mobile health, causal marketing etc . As a dynamic approach, it can be more efficient than standard A/B testing in minimizing regret. We propose an end to end automated meta-learning pipeline…

2019-09-07abs ↗pdf ↗

Optimising Individual-Treatment-Effect Using Banditscs.LG

Applying causal inference models in areas such as economics, healthcare and marketing receives great interest from the machine learning community. In particular, estimating the individual-treatment-effect (ITE) in settings such as precision medicine and targeted advertising has peaked in application. Optimising this IT…

2019-10-16abs ↗pdf ↗

Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modelingstat.ML

New estimator improves off-policy evaluation for large action spaces.

problem Conventional importance-weighting approaches suffer from excessive variance in off-policy evaluation for large discrete action spaces.

method Proposes OffCEM estimator based on conjunct effect model (CEM), applying importance weighting only to action clusters and using model-based reward estimation for residual effects.

result Proposed estimator is unbiased under local correctness condition, providing substantial improvements in OPE especially with many actions.

Off-policy evaluation Contextual bandits Large action spaces Conjunct effect model Importance weighting

2023-05-14abs ↗pdf ↗