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.

168,695 papers · 148 categories

Trend · papers per month

2457 · Jun 202019922001200920172026
48 results for bandit-learning

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.

Study on the limits of bandit learning, showing hardness and limitations.

problem Understanding the learnability of bandit learning under arbitrary reward functions.
method Investigation into which classes of reward functions are learnable and how they can be learned.
result No combinatorial dimension can characterize bandit learnability, and computational hardness is inherent.

Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.

problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg(ε)(ε) algorithm that aggregates rewards from different players.
result Achieves instance-dependent regret guarantees and nearly matching lower bounds.

Paper introduces a bandit-learning method for multifidelity approximations.

problem Efficiently using data of varying fidelities in scientific computation.
method Formulates multifidelity approximation as a modified stochastic bandit problem and proposes AETC algorithm.
result Established optimality of AETC algorithm for multifidelity approximation.

Gaussian prior and likelihood improve bandit learning performance.

problem Improving bandit learning with misspecified Gaussian distributions.
method An agent with a bounded information ratio interacts with a Bernoulli bandit based on a Gaussian prior and likelihood.
result The regret increase is at most linear in the square-root of the time horizon for diffuse distributions.

Paper tackles federated linear bandit learning with AirComp for noisy channels.

problem Minimize cumulative regret in federated linear bandit learning.
method Proposes a federated linear bandits scheme using over-the-air computation (AirComp) over noisy fading channels.
result Determines the regret bound of the proposed scheme.

Adaptive compute allocation improves model performance by prioritizing harder queries.

problem Inefficiency in allocating test-time compute uniformly across all queries.
method Formulated as a bandit learning problem, proposed adaptive algorithms that estimate query difficulty and allocate compute accordingly.
result Achieved up to 15.29% relative performance improvement on various benchmarks.

We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logge…

2018-04-16abs ↗pdf ↗

We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine tra…

2017-07-27abs ↗pdf ↗

We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of KK actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problem…

2014-02-04abs ↗pdf ↗

New learning methods for open systems with variable agents.

problem Learning in open systems with dynamic agent arrivals and departures.
method Formulated a unified open-system bandit problem with general dynamics, introducing new concepts like pre-training degree and stability.
result Certified global-UCB learning methodologies with provable guarantees, revealing dependencies between entry uncertainty, stability, and agent patterns.

The paper analyzes Random Search and introduces BLiN-MOS for bandit learning.

problem Understanding and optimizing hyperparameter tuning in metric measure spaces.
method Introducing scattering dimension to quantify performance, and developing BLiN-MOS for bandit learning.
result Random Search converges to optimal values with specific rates in noise-free and noisy environments.

Predictive sampling improves on Thompson sampling for non-stationary bandit environments.

problem Thompson sampling fails in non-stationary bandit environments.
method Proposes predictive sampling, which deprioritizes actions based on information loss rate.
result Predictive sampling outperforms Thompson sampling in all tested non-stationary environments.

The study explores whether model selection guarantees apply to contextual bandits.

problem Applying model selection guarantees to contextual bandits.
method Investigates whether similar guarantees for model selection in statistical learning can be extended to contextual bandit learning.
result Initial findings suggest that model selection guarantees may not directly apply to contextual bandits.

New algorithm for learning preferences in decentralized matching markets reduces regret to logarithmic levels.

problem Learning preferences in decentralized matching markets without direct communication.
method Introduces a new algorithm for two-sided matching markets with competition.
result The algorithm achieves logarithmic stable regret in shared preferences and quadratic regret in general preferences.

Improved regret bounds for structured linear contextual bandits with Gaussian noise.

problem Optimizing bandit learning algorithms for structured contexts with Gaussian perturbations.
method Proposed simple greedy algorithms for structured linear contextual bandits with Gaussian noise.
result Unified regret analysis for structured parameters with geometric quantities as bounds.

A new framework for optimizing interventions with limited data.

problem Small data, default intervention data, unmodeled objectives, unforeseen consequences.
method Bandit data-driven optimization combining online bandit learning and offline predictive analytics.
result PROOF algorithm achieves no-regret and superior performance in simulations and real-world application.

Paper tackles constrained bandit problems with a new learning framework.

problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

problem Real-world distributed decision-making with imperfect communication.
method Proposed decentralized algorithms for three communication scenarios: stochastic networks, random delays, and adversarially corrupted rewards.
result Achieved competitive performance and near-optimal guarantees on group regret.

Adaptive algorithms minimize regret in matching markets with contextual arm preferences.

problem Minimizing regret in matching markets with context-dependent player utilities.
method Developed adaptive algorithms for stochastic and adversarial contexts, providing upper and lower bounds.
result Achieved sublinear regret bounds for both stochastic and adversarial contexts.

This article introduces the concepts around Online Bandit Linear Optimization and explores an efficient setup called SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a O(T)O(\sqrt{T}) regret bound and polynomial run time comple…

2018-05-11abs ↗pdf ↗

Framework reduces contextual bandit learning to offline regression with near-optimal regret.

problem Efficient learning with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that minimizes regret with near-optimal oracle calls.
result Near-optimal regret for contextual bandits with large action spaces and O(log(T))O(log(T)) offline oracle calls.

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.

Algorithm solves two-sided matching markets with unknown preferences and constraints.

problem Two-sided online matching markets with complementary preferences and quota constraints.
method Formulated as a bandit learning problem, proposed MMTS algorithm combining Thompson Sampling and double matching.
result MMTS achieves stability and linear Bayesian regret with respect to quota and time horizon.

Paper stabilizes bandit learning with regularization, improving inference under adaptive sampling.

problem Challenges in statistical inference with adaptive sampling.
method Refined stability condition for online algorithms, using regularized stochastic-mirror-descent-style methods.
result Derives precise regret bounds and asymptotic normality, showing necessity of regularization for valid inference.

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 ↗

In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support. While our current use cases focus on single step einforcement learning (RL) and mostly in the domain of natural language proce…

2019-05-06abs ↗pdf ↗

LNUCB-TA improves MAB performance by dynamically adjusting exploration rates and recognizing spatiotemporal patterns.

problem Suboptimal performance in environments with rapidly changing reward structures and static exploration rates.
method Hybrid model combining linear and nonlinear estimation, with adaptive k-NN for temporal attention.
result Significantly outperforms state-of-the-art algorithms in cumulative and mean reward, convergence, and robustness.

A new method for energy-efficient file delivery in small cell networks.

problem Efficient resource management in femto-caching with time-variant statistical properties.
method Formulates a resource allocation problem as a stochastic knapsack problem and a multi-armed bandit problem, developing solutions for each.
result The proposed method maximizes the accumulated utility over the horizon, especially suitable for networks with time-variant statistical properties.

New algorithm for bandits with delayed action effects, reducing regret.

problem Delayed impact of actions in multi-armed bandits.
method Formulated a new bandit setting with delayed action effects, proposed an algorithm with regret bound.
result Achieved a regret of ildeO(KT2/3) ilde{\mathcal{O}}(KT^{2/3}) and showed a matching lower bound.

This paper uses bandit theory and Thompson Sampling to optimize protein sequences.

problem Optimizing protein sequences using machine learning and directed evolution.
method Proposes a Thompson Sampling-guided Directed Evolution (TS-DE) framework.
result TS-DE achieves a nearly optimal Bayesian regret of order ildeO(d2MT) ilde O(d^{2}\sqrt{MT}).

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…

2017-04-21abs ↗pdf ↗

In many platforms, user arrivals exhibit a self-reinforcing behavior: future user arrivals are likely to have preferences similar to users who were satisfied in the past. In other words, arrivals exhibit positive externalities. We study multiarmed bandit (MAB) problems with positive externalities. We show that the self…

2018-02-15abs ↗pdf ↗

This work introduces reward teaching for federated multi-armed bandits to guide clients towards global optimality.

problem Existing federated multi-armed bandits designs assume clients will follow the server's protocol, but this is not always feasible.
method Introduces reward teaching where the server adjusts clients' local rewards to encourage global optimality, using phased Teaching-After-Learning (TAL) and Teaching-While-Learning (TWL) algorithms.
result Demonstrates that TAL achieves logarithmic regrets with only logarithmic adjustment costs, and TWL outperforms TAL for UCB1 clients.

A popular approach to selling online advertising is by a waterfall, where a publisher makes sequential price offers to ad networks for an inventory, and chooses the winner in that order. The publisher picks the order and prices to maximize her revenue. A traditional solution is to learn the demand model and then subseq…

2019-04-20abs ↗pdf ↗

Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsa…

2019-07-01abs ↗pdf ↗

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically …

2012-06-27abs ↗pdf ↗

Eluder dimension and information gain are equivalent for reproducing kernel Hilbert spaces.

problem Complexity measures in bandit and reinforcement learning.
method Equivalence of eluder dimension and information gain for reproducing kernel Hilbert spaces.
result Eluder dimension and information gain are equivalent for reproducing kernel Hilbert spaces.