Optimal resource allocation in censored semi-bandits with unknown thresholds.
problem Sequential resource allocation with unknown thresholds and hidden parameters.
method Established equivalence to MP-MAB and Combinatorial Semi-Bandits, derived optimal algorithms.
result Validated performance of proposed algorithms on synthetic data.
In this paper, we study censored Semi-Bandits, a novel variant of the semi-bandits problem. The learner is assumed to have a fixed amount of resources, which it allocates to the arms at each time step. The loss observed from an arm is random and depends on the amount of resources allocated to it. More specifically, the…
Algorithm allocates budgets to tasks with semi-bandit feedback, achieving near-optimal regret bounds.
problem Stochastic budget allocation with censored semi-bandit feedback.
method Optimism-based algorithm operating under censored semi-bandit feedback.
result Regret scales polylogarithmically with horizon T in diminishing-returns regimes.
Polynomial-time method solves complex combinatorial semi-bandits.
problem Optimal strategies for combinatorial semi-bandits with uncorrelated Gaussian rewards.
method Proposes a polynomial-time method to solve the Graves-Lai optimization problem for various combinatorial structures.
result First known approach to implement asymptotically optimal algorithms in polynomial time for combinatorial semi-bandits.
This paper improves FTPL algorithm for semi-bandit problems with best-of-both-worlds guarantees.
problem Optimizing regret in adversarial and stochastic m m m -set semi-bandit problems. method Extending FTPL with geometric resampling (GR) to m m m -set semi-bandits and analyzing its performance. result FTPL with Fréchet and Pareto distributions achieves O ( m d T ) O(\sqrt{mdT}) O ( m d T ) regret in adversarial setting and logarithmic regret in stochastic setting. Paper analyzes FTPL's effectiveness in combinatorial semi-bandit problems.
problem Optimizing FTPL policy in combinatorial semi-bandit problems.
method Geometric resampling (GR) and conditional geometric resampling (CGR) for FTPL in semi-bandit setting.
result FTPL achieves optimal regret bounds in both Fréchet and Pareto distributions.
FTPL with Fréchet perturbation achieves near optimal regret bounds for m-set semi-bandit problems.
problem Optimizing regret bounds for m-set semi-bandit problems in adversarial and stochastic settings.
method Follow-the-Perturbed-Leader (FTPL) with Fréchet perturbation.
result Achieves near optimal regret bounds of O ( n m ( d log ( d ) + m 5 / 6 ) ) \mathcal{O}(\sqrt{nm}(\sqrt{d\log(d)}+m^{5/6})) O ( nm ( d log ( d ) + m 5/6 )) in adversarial setting and logarithmic regret in stochastic setting. We develop the first general semi-bandit algorithm that simultaneously achieves O ( log T ) \mathcal{O}(\log T) O ( log T ) regret for stochastic environments and O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret for adversarial environments without knowledge of the regime or the number of rounds T T T . The leading problem-dependent constants of our bounds are …
This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.
problem Adversarial combinatorial semi-bandits with graph feedback.
method Introduced graph feedback in combinatorial semi-bandits, using convexified actions and online stochastic mirror descent.
result Optimal regret scales as S T + α S T S\sqrt{T}+\sqrt{αST} S T + α S T , interpolating between full and semi-bandit feedback. Optimistic covariance-adaptive algorithms improve combinatorial semi-bandits regret.
problem Optimal regret in stochastic combinatorial semi-bandits with adaptive covariance estimation.
method Design of OLS-UCB-C and COS-V algorithms leveraging online covariance estimation.
result Improved gap-free regret with T^1/2 complexity for COS-V.
Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.
problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret with O ( log log T ) O(\log\log T) O ( log log T ) oracle queries for worst-case linear rewards. We investigate the piecewise-stationary combinatorial semi-bandit problem. Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at unknown time steps. We propose an algorithm, \texttt{GLR-CUCB}, which incorporat…
Study optimal arms in combinatorial bandits with semi-bandit feedback and finite budget.
problem Finding optimal arms in combinatorial bandits with semi-bandit feedback and finite budget constraints.
method Proposes a generic algorithm covering various arm elimination strategies and derives lower bounds.
result Demonstrates sufficient and necessary budget requirements for finding the best arm.
Unified framework for analyzing online convex optimization across various settings.
problem Analyzing online convex optimization in different settings and feedback types.
method Unified framework allowing systematic proposal and analysis of meta-algorithms.
result Comparable regret bounds for various feedback types and adversary types.
This paper addresses issues with the Brier score in administrative censoring scenarios.
problem Problems with the Brier score in administrative censoring scenarios.
method Proposes an alternative Brier score for administratively censored data.
result The administrative Brier score is valid even when censoring times can be identified from covariates.
New algorithm reduces semi-bandit regret using covariance estimates.
problem Complexity of semi-bandits due to joint distribution of outcomes.
method Develops a new sub-exponential distribution family and an algorithm using covariance estimates.
result Proves a new lower bound on expected regret and constructs an algorithm with asymptotic analysis.
Improved statistical efficiency of Thompson Sampling for combinatorial semi-bandits.
problem Efficiency of policies in stochastic combinatorial multi-armed bandits with semi-bandit feedback.
method Analysis of Combinatorial Thompson Sampling (CTS) using Beta and Gaussian priors for mutually independent and multivariate sub-Gaussian outcomes.
result CTS provides an efficient policy with optimal asymptotic regret for both mutually independent and multivariate sub-Gaussian outcomes.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
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.
New algorithm reduces combinatorial semi-bandit regret efficiently.
problem Optimizing rewards from uncorrelated items in combinatorial semi-bandits.
method Developed an approximate version of ESCB with polynomial complexity.
result Achieved statistically efficient and polynomial time algorithm for combinatorial semi-bandits.
New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.
problem Fair selection in stochastic combinatorial semi-bandit with delayed feedback.
method Introduced merit-based fairness constraints and new bandit algorithms for reward and fairness.
result Achieved sublinear expected reward and fairness regrets with dependence on delay distribution quantiles.
We improve the efficiency of algorithms for stochastic \emph{combinatorial semi-bandits}. In most interesting problems, state-of-the-art algorithms take advantage of structural properties of rewards, such as \emph{independence}. However, while being optimal in terms of asymptotic regret, these algorithms are inefficien…
A new boosting model handles dependent censoring in time-to-event data.
problem Independent censoring assumption leads to biased predictions in time-to-event analysis.
method Clayton-boost, a boosting approach using Clayton copula.
result Clayton-boost outperforms other methods in handling dependent censoring.
Develops a combinatorial semi-bandit method for electric vehicle charging station selection.
problem Long-distance navigation for BEVs with unknown charging station availability and performance.
method Combinatorial semi-bandit framework, pre-processing road network, Bayesian modeling, Thompson Sampling, BayesUCB, Epsilon-greedy.
result Demonstrates improved navigation performance on long-distance BEV charging station selection.
Coop-FTPL algorithm minimizes network regret in semi-bandit settings.
problem Online combinatorial optimization with semi-bandit feedback on a network of agents.
method Cooperative Follow The Perturbed Leader (Coop-FTPL) algorithm with new loss estimation procedure.
result Expected regret of Coop-FTPL is of order Q mkT log(k)(kα1 /Q + m), with a state-of-the-art computational complexity of T^3/2.
Develops a method to estimate quantiles in censored data using random forests.
problem Inability of random forests to handle randomly censored observations.
method Regression adjustment for quantile regression models based on a new estimating equation.
result Consistent estimation of quantiles without parametric modeling assumptions.
Algorithm improves movie recommendation efficiency with fairness constraints.
problem Improving movie recommendation efficiency with fairness constraints in combinatorial semi-bandits.
method Adopted Thompson Sampling with beta priors and Bernoulli likelihoods to handle fairness constraints.
result Time-averaged regret upper bounded by $\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}
ight)$ , with fairness constraints satisfied.
This paper introduces a multi-output Gaussian process for censored data.
problem Modeling bias in censored data using correlations between multiple outputs.
method Heteroscedastic multi-output Gaussian process with input-dependent noise and variational inference.
result The model better estimates the true process under complex censoring dynamics.
Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.
problem Identifying the best arm in combinatorial bandits with semi-bandit feedback.
method Interpreted as a sequential zero-sum game, developed a CombGame meta-algorithm with finite time guarantees.
result First computationally efficient algorithm that is asymptotically optimal and has competitive empirical performance.
DAERNN models censored data using neural networks with data augmentation.
problem Handling censored data in expectile regression.
method Data augmentation based Expectile Regression Neural Networks (ERNNs).
result DAERNN outperforms existing censored ERNNs methods and achieves comparable predictive performance to fully observed data.
Study improves risk evaluation timing with right-censored reporting delays.
problem Improving risk evaluation under short observation windows due to administrative censoring.
method Jointly models parametric hazards for event and reporting processes, uses Monte Carlo expectation-maximization algorithm, and proposes transfer-learning procedure.
result Improves accuracy of timely risk evaluation under administrative censoring.
New algorithm tackles non-stationary combinatorial semi-bandit problems with optimal regret bounds.
problem Non-stationary combinatorial semi-bandit problems in switching and dynamic environments.
method Developed algorithms for both switching and dynamic cases, achieving nearly optimal regret bounds.
result Achieved nearly optimal regret bounds in both switching and dynamic cases.
New metric reduces estimation error in survival model evaluation.
problem Dependent censoring complicates survival model evaluation.
method Dependent Brier score based on Archimedean copula and Copula-Graphic estimator.
result Reduces estimation error by 12-16% on average.
New experimental design minimizes regret in bandits.
problem Minimizing regret in online stochastic linear and combinatorial bandits.
method Experimental design-based algorithm balancing information gain and reward.
result State-of-the-art finite time regret guarantees and computational efficiency.
New method generates synthetic survival data by conditioning on event times and censoring indicators.
problem Generating accurate synthetic survival data with censored event times.
method Conditioning covariates on event times and censoring indicators using existing tabular data generation models.
result Our method consistently outperforms baselines and improves survival model performance.
The paper benchmarks OS with RCTs, accounting for right-censoring.
problem Benchmarking observational studies with experimental data under censoring.
method Two cases: independent and dependent censoring. Censoring-doubly-robust signal for CATE.
result Effectiveness of censoring-aware tests verified via experiments and real data.
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.
Random forests are powerful non-parametric regression method but are severely limited in their usage in the presence of randomly censored observations, and naively applied can exhibit poor predictive performance due to the incurred biases. Based on a local adaptive representation of random forests, we develop its regre…
A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we close the problem of computationally and sample effi…
Efficient neural Bayes estimators for censored peaks-over-threshold models improve inference speed and accuracy.
problem Computational burden in inference with spatial extremal dependence models due to intractable or censored likelihoods.
method Developed neural Bayes estimators using data augmentation techniques to encode censoring information.
result Significant gains in computational and statistical efficiency compared to traditional methods.
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.
A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to combinatorial constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we consider efficient learning in large-s…
Bayesian active learning method improved for censored regression data.
problem Challenges in estimating BALD for censored regression data.
method Derived entropy and mutual information for censored distributions, developed C \mathcal{C} C -BALD objective, proposed novel modelling approach. result Demonstrated C \mathcal{C} C -BALD outperforms other methods in censored regression. New methods improve off-policy evaluation for survival outcomes with censoring.
problem Systematic underestimation of policy performance due to censoring bias in survival outcomes.
method Proposes IPCW-IPS and IPCW-DR to handle censoring bias in survival outcomes.
result The proposed methods are unbiased and achieve double robustness.
Survival forests estimate treatment effects with censored data.
problem Estimating treatment effects in survival analysis with censored data.
method Causal survival forests using orthogonal estimating equations.
result Survival forests perform well relative to baselines in treatment effect estimation.
Study learns Gaussian mixtures from censored data.
problem Learning Gaussian mixtures with incomplete data.
method Proposes an algorithm to estimate weights and means with minimal samples.
result Achieves accurate estimation with very few samples.
We propose a nonparametric test of independence, termed optHSIC, between a covariate and a right-censored lifetime. Because the presence of censoring creates a challenge in applying the standard permutation-based testing approaches, we use optimal transport to transform the censored dataset into an uncensored one, whil…
Optimizes matching in weighted graphs with semi-bandit sampling.
problem Finding optimal pairings in weighted graphs with sequential sampling.
method Leverages rank-1 assumption on adjacency matrix to reduce sample complexity and regret.
result Achieves linear dependency in the number of vertices for sample complexity and regret.