Research
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

88177265353 · Jun 202019922001200920172026
48 results for stochastic delayed feedback

We study a variant of the stochastic KK-armed bandit problem, which we call "bandits with delayed, aggregated anonymous feedback". In this problem, when the player pulls an arm, a reward is generated, however it is not immediately observed. Instead, at the end of each round the player observes only the sum of a number…

2017-09-20abs ↗pdf ↗

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.

Online learning with delayed feedback has received increasing attention recently due to its several applications in distributed, web-based learning problems. In this paper we provide a systematic study of the topic, and analyze the effect of delay on the regret of online learning algorithms. Somewhat surprisingly, it t…

2013-06-04abs ↗pdf ↗

Improved algorithm for bandits with delayed feedback, combining adversarial and stochastic performance.

problem Adversarial and stochastic multiarmed bandits with delayed feedback.
method Modified Zimmert and Seldin's algorithm with near-optimal regret guarantees.
result Near-optimal regret guarantees in both adversarial and stochastic settings.

Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by practitioners hoping to apply existing algorithms is that usually the feedback is randomly …

2018-07-05abs ↗pdf ↗

We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback. The delay in feedback increases the effective sample complexity of standard algorithms, but can be offset if we have access to partial…

2018-03-29abs ↗pdf ↗

New algorithm tackles non-stationary delayed feedback in recommender systems.

problem Challenges in learning from delayed feedback in non-stationary environments.
method Developed a UCRL-based algorithm for non-stationary, delayed bandits with intermediate observations.
result Sublinear regret guarantees for the proposed algorithm in non-stationary delayed environments.

New RL algorithm handles delayed feedback with posterior sampling.

problem Challenges of delayed feedback in reinforcement learning with linear function approximation.
method Posterior sampling with delayed feedback for value-based RL.
result Achieves optimal regret guarantee with improved computational efficiency.

We explore a novel setting of the Multi-Armed Bandit (MAB) problem inspired from real world applications which we call bandits with "stochastic delayed composite anonymous feedback (SDCAF)". In SDCAF, the rewards on pulling arms are stochastic with respect to time but spread over a fixed number of time steps in the fut…

2019-10-02abs ↗pdf ↗

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

problem Optimizing unknown functions with noisy, delayed, and multi-fidelity feedbacks.
method ProCrastinated Tree Search (PCTS) with DUCB1 and DUCBV algorithms.
result PCTS achieves better regret bounds for delayed, noisy, and multi-fidelity feedbacks.

New algorithm handles delayed feedback robustly, reducing regret without knowing delay bounds.

problem Bandits with variably delayed feedback, especially excessive delays.
method Implicit exploration scheme, adaptive skipping, drifted regret control.
result Can tolerate arbitrary excessive delays up to order T, reducing regret.

The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback. As the main result, we develop the General Hedging algorithm G\mathcal{G} based on the exponential reweighing of experts' losses. We build the artificial probabilistic framework and …

2019-02-27abs ↗pdf ↗

Study online learning with delays and capacity constraints, achieving optimal regret bounds.

problem Online learning with delays and capacity constraints.
method Novel scheduling and preemptive techniques, matching upper and lower bounds.
result Achieves optimal regret bounds across all capacity levels.

New algorithms handle online prediction with bandit and delayed feedback, improving regret bounds.

problem Achieving finite bounds on surrogate regret with limited feedback.
method Proposed algorithms for bandit and delayed feedback, including inverse-weighted gradient and pseudo-inverse matrix estimators.
result Achieved improved surrogate regret bounds of O(KT)O(\sqrt{KT}) and O(T2/3)O(T^{2/3}).

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.

Predicting conversion rates (CVRs) in display advertising (e.g., predicting the proportion of users who purchase an item (i.e., a conversion) after its corresponding ad is clicked) is important when measuring the effects of ads shown to users and to understanding the interests of the users. There is generally a time de…

2018-02-01abs ↗pdf ↗

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

problem Adversarial bandit problem with delayed, composite anonymous feedback.
method Propose wrapper algorithm for non-oblivious delay setting, achieving o(T)o(T) policy regret.
result Achieve o(T)o(T) policy regret for many adversarial bandit problems with bounded memory loss sequences.

This paper deals with bandit online learning problems involving feedback of unknown delay that can emerge in multi-armed bandit (MAB) and bandit convex optimization (BCO) settings. MAB and BCO require only values of the objective function involved that become available through feedback, and are used to estimate the gra…

2018-07-09abs ↗pdf ↗

Improved online convex optimization with delayed feedback using curvature.

problem Online convex optimization with curved losses and delayed feedback.
method Variant of follow-the-regularized-leader and Online Newton Step algorithm with adaptive learning rate.
result Regret bounds of order min{σmaxlnT,dtot}\min\{σ_{\max}\ln T, \sqrt{d_{\mathrm{tot}}}\} for exp-concave losses.

The paper develops methods for time-varying constrained online convex optimization.

problem Time-varying loss and constraint functions in online convex optimization.
method Model-based augmented Lagrangian methods (MALM) for time-varying and delayed feedback.
result Sublinear regret and constraint violation for both time-varying and delayed feedback scenarios.

New algorithm tackles multi-armed bandit with arbitrary delays and general bounded losses.

problem Scale-free adversarial multi-armed bandit with arbitrary feedback delays.
method SFD-INF combines convex combination trick and doubling/skipping technique.
result Achieves adaptive regret bounds for non-negative and general scale-free losses.

Delaytron learns multi-class classifiers with delayed feedbacks, achieving efficient regret bounds.

problem Learning multi-class classifiers with delayed bandit feedbacks where delays are unknown.
method Online algorithm Delaytron with adaptive learning for unknown delays.
result Achieves efficient regret bounds for various loss scenarios.

Proposes a method to train classifiers with delayed feedback using a time window.

problem Training classifiers with delayed feedback that can be biased due to delayed user actions.
method Uses a time window to select samples for training, constructs unbiased empirical risk from all samples.
result Improves classifier performance by using all samples with a time window assumption.

New algorithm for multi-armed bandits with delayed, partially observed rewards.

problem Sequential decision-making with delayed feedback.
method Proposed multi-armed bandits with generalized temporally-partitioned rewards, introducing β-spread property.
result Upper bound on performance of TP-UCB-FR-G algorithm improves state of the art.

New algorithm reduces dynamic regret in time-varying movement costs.

problem Dynamic regret in online convex optimization with time-varying movement costs.
method Introduced a novel algorithm for time-varying movement costs, achieving comparator-adaptive dynamic regret bound.
result Established first comparator-adaptive dynamic regret bound of O~((M2+MPT)(T+tλt))\widetilde{\mathcal{O}}(\sqrt{(M^2+MP_T)(T+\sum_t λ_t)}).

Proposes neural delay differential equations for stable system identification with partially observed states.

problem Learning stable models for systems with partial or delayed observations.
method Augments states with history, uses neural delay differential equations, and ensures stability through time delay analysis.
result The approach ensures stability of learned models for partially observed systems.

New algorithm tackles stochastic bandits with varying arm-dependent delays.

problem Applying existing algorithms to stochastic delayed bandit settings is restricted by strong assumptions on delay distributions.
method Proposes a simple UCB-based algorithm called PatientBandits that weakens assumptions on delay distributions.
result Provides bounds on regret and performance lower bounds for the PatientBandits algorithm.

We consider a stochastic multi-armed bandit (MAB) problem with delayed impact of actions. In our setting, actions taken in the past impact the arm rewards in the subsequent future. This delayed impact of actions is prevalent in the real world. For example, the capability to pay back a loan for people in a certain socia…

2020-02-24abs ↗pdf ↗

New algorithm for decentralized online convex optimization with unknown delays.

problem Decentralized online convex optimization with unknown, time-varying feedback delays.
method Proposes a novel algorithm that incorporates adaptive learning rates and gossip-based delay estimation.
result Achieves improved regret bounds of O(N √d tot + N √T (1-σ^2)^(1/4)) and O(N δmax ln T α) for different settings.