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

305989118 · Jun 202019922001200920172026
48 results for Extreme Bandits

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific task of choosing among distributions to use for random hyperparameter optimization.…

2015-08-12abs ↗pdf ↗

This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose…

2017-07-27abs ↗pdf ↗

New method reduces bias in learning from large action spaces using selective importance sampling.

problem Learning from large-scale recommendation systems with bandit feedback and supervised labels.
method Selective Importance Sampling (sIS) and Policy Optimization for eXtreme Models (POXM) algorithm.
result POXM method significantly outperforms existing methods in learning from bandit feedback on XMC tasks.

A new algorithm for selecting top-k arms in extreme contextual bandits with improved efficiency.

problem Selecting top-k arms from a large set with contextual information and limited rewards.
method Proposes an algorithm for both non-extreme and extreme settings, using Inverse Gap Weighting and arm hierarchy models.
result Achieves improved regret guarantees for extreme settings with significant computational and statistical efficiency.

A new method optimizes in nonstationary environments with many arms efficiently.

problem Optimizing in nonstationary environments with a large number of arms.
method Gaussian interpolation to learn continuous Lipschitz reward functions in nonstationary environments.
result Efficiently learns continuous Lipschitz reward functions with O(T)\mathcal{O}^*(\sqrt{T}) cumulative regret.

We study the restless bandit associated with an extremely simple scalar Kalman filter model in discrete time. Under certain assumptions, we prove that the problem is indexable in the sense that the Whittle index is a non-decreasing function of the relevant belief state. In spite of the long history of this problem, thi…

2015-09-15abs ↗pdf ↗

Improves bandits with knapsacks guarantees for partially stochastic workloads.

problem Improves guarantees for Bandits with Knapsacks (BwK) with partially stochastic workloads.
method Defines Approximately Stationary BwK, explores algorithms with smooth competitive ratios transitioning between stochastic and adversarial cases.
result Offers competitive ratios that smoothly transition between the best possible guarantees in stochastic and adversarial cases, especially beneficial when budget is small.

Existing strategies for finite-armed stochastic bandits mostly depend on a parameter of scale that must be known in advance. Sometimes this is in the form of a bound on the payoffs, or the knowledge of a variance or subgaussian parameter. The notable exceptions are the analysis of Gaussian bandits with unknown mean and…

2017-03-27abs ↗pdf ↗

New meta-learning approach for bandit policies that achieve high average reward.

problem Designing bandit policies that balance between worst-case and Bayesian assumptions.
method Differentiable parameterized policies optimized using policy gradients.
result Proposed algorithm achieves low regret and is practical for various bandit problems.

Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e.g., online advertisements. In the era of big data, contextual data usually tend to be high-dimensional, which leads to new challenges for traditional l…

2019-03-20abs ↗pdf ↗

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.

Study lenient regret and good-action identification in Gaussian process bandits.

problem Optimizing function values above a certain threshold in Gaussian process bandits.
method Study lenient regret notions and introduce algorithms for finding good actions.
result Upper and lower bounds on lenient regret for GP-UCB and elimination algorithms.

New algorithms reduce dueling bandits' regret with neural networks and efficient exploration.

problem Optimizing dueling bandits with neural networks for better performance.
method Combines shallow exploration strategies with neural networks for utility approximation, using iterative self-improvement and spectral analysis to reduce network width.
result Achieves sublinear regret of O~(dt=1Tσt2+dT)\widetilde{\mathcal{O}}(d\sqrt{\sum_{t=1}^{T} σ_t^2} + \sqrt{dT}).

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely fix sequences of arm selections before observing rewards, our method adaptively c…

2017-10-16abs ↗pdf ↗

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}).

We consider Bandits with Knapsacks (henceforth, BwK), a general model for multi-armed bandits under supply/budget constraints. In particular, a bandit algorithm needs to solve a well-known knapsack problem: find an optimal packing of items into a limited-size knapsack. The BwK problem is a common generalization of nume…

2018-11-28abs ↗pdf ↗

We consider the Lipschitz bandit optimization problem with an emphasis on practical efficiency. Although there is rich literature on regret analysis of this type of problem, e.g., [Kleinberg et al. 2008, Bubeck et al. 2011, Slivkins 2014], their proposed algorithms suffer from serious practical problems including extre…

2019-04-25abs ↗pdf ↗

Paper optimizes FTPL for adversarial and stochastic bandits with specific tail distributions.

problem Optimizing Follow-the-Perturbed-Leader (FTPL) policy for bandit problems.
method Analyzes FTPL with Fréchet-type tail distributions in adversarial and stochastic settings.
result FTPL with certain Fréchet-type tail distributions achieves O(KT)\mathcal{O}(\sqrt{KT}) regrets in adversarial bandits.

Solves action selection for large spaces in RL, achieving near-optimal performance.

problem Selecting a small, representative subset of actions from a large, shared action space.
method Extends meta-bandit approach to MDPs, using a relaxed sub-Gaussian process model.
result Achieves performance comparable to full action space, with theoretical guarantees.

Mortal bandits have proven to be extremely useful for providing news article recommendations, running automated online advertising campaigns, and for other applications where the set of available options changes over time. Previous work on this problem showed how to regulate exploration of new arms when they have recen…

2019-07-04abs ↗pdf ↗

Two algorithms achieve optimal regret with limited adaptivity in multinomial logistic bandits.

problem Achieving optimal regret with limited adaptivity in multinomial logistic bandits.
method Presented two algorithms, B-MNL-CB and RS-MNL, for batched and rarely-switching paradigms.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) regret with limited adaptivity.

This paper tightens the law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.

problem Developing nonasymptotic concentration bounds for empirical KL_inf with optimal constants and rates.
method Presenting a tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
result A tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.

AdaPrivate-TS: A differentially private Thompson Sampling algorithm for contextual bandits

problem Private Thompson Sampling for Contextual Bandits
method Combining Thompson Sampling with batched zCDP composition
result Achieves 93-99% of non-private performance at ε ∈ [0.5, 5] with logarithmic privacy cost

A new offline RL framework unifies imitation learning and vanilla offline RL.

problem Learning from expert datasets without active data collection.
method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.
result LCB algorithm achieves a faster rate of 1/N1/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range.

New OPE estimator improves offline policy evaluation for large action spaces.

problem Existing OPE estimators fail with large action spaces, leading to extreme bias and variance.
method Proposes a new estimator using marginalized importance weights and action embeddings.
result Empirical performance improvement enables reliable OPE even with many actions.

The goal of data-driven algorithm design is to obtain high-performing algorithms for specific application domains using machine learning and data. Across many fields in AI, science, and engineering, practitioners will often fix a family of parameterized algorithms and then optimize those parameters to obtain good perfo…

2019-04-18abs ↗pdf ↗

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.

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

problem Stochastic contextual linear bandits with unknown context distribution.
method Establishes a reduction framework to convert to linear bandit problems.
result Achieves nearly optimal regret bound of O(dTlogT)O(d\sqrt{T\log T}).

Graph-Triggered Bandits unify rested and restless bandits with graph-defined arm interactions.

problem Modeling sequential decision-making problems with evolving arm rewards.
method Graph-Triggered Bandits (GTBs) framework that generalizes rested and restless bandits using a graph.
result Rested and restless bandits are special cases of GTBs for suitable graphs.

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.