We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized prediction, allowing the model to update its weak learners with limited information. …
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
48 results for “bandit learners”
Observer learns optimal policy from learner's actions without rewards.
problem Learning optimal policy from non-rewarded actions of a non-stationary learner.
method Two-Phase Suffix Imitation framework.
result Observer achieves convergence rate of .
There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…
We consider a multiobjective multiarmed bandit problem with lexicographically ordered objectives. In this problem, the goal of the learner is to select arms that are lexicographic optimal as much as possible without knowing the arm reward distributions beforehand. We capture this goal by defining a multidimensional for…
Study the tradeoffs of bandit feedback in multiclass classification.
problem The price of using bandit feedback in multiclass classification.
method Mistake bound model, analysis of variants, and comparison of learners and adversaries.
result The optimal mistake bound under bandit feedback is at most times higher than in full information, with a tight bound of .
Algorithm improves online learning in adversarial bandits.
problem Online learning in adversarial multi-armed bandits with non-uniform best arm distribution.
method Online-within-online setup, inner and outer learners, leveraging non-uniform empirical distribution of best arms.
result Improves regret bounds for non-uniform best arm distributions.
This paper optimizes attacks on stochastic bandits and proposes defenses against them.
problem Optimizing adversarial attacks on stochastic bandit algorithms.
method Designs optimal attack strategies and proposes defense algorithms.
result Optimal attack strategies and defense algorithms achieve near perfect performance.
Meta-learning improves performance across similar tasks in adversarial bandit settings.
problem Improving performance across multiple similar tasks in adversarial bandit scenarios.
method Designing meta-algorithms that combine outer learners to tune hyperparameters of inner learners for MAB and BLO.
result Meta-algorithms improve task-averaged regret for MAB and BLO, showing direct relationship with action space-dependent measures.
Compliance-Aware Banditsstat.ML
Motivated by clinical trials, we study bandits with observable non-compliance. At each step, the learner chooses an arm, after, instead of observing only the reward, it also observes the action that took place. We show that such noncompliance can be helpful or hurtful to the learner in general. Unfortunately, naively i…
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.
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradoxstat.ML
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.
Data-driven model selection reduces regret in sequential decisions.
problem Optimizing model selection in stochastic environments with bandit feedback.
method Data-driven regret balancing for model selection.
result Meta-learner selects the best base learner based on actual realized regret.
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.
Optimizes decision-making in dueling bandits with contextual features.
problem Identifying the best arm in dueling bandits with contextual features.
method Develops algorithms for minimizing regret in stochastic contextual dueling bandits.
result Proves optimal regret bounds for contextual dueling bandits.
Study best arm identification with limited precision sampling in bandits.
problem Limited precision sampling in multi-armed bandit problems.
method Proposed a modified tracking-based algorithm to handle non-unique optimal allocations and presented non-asymptotic bounds.
result Asymptotically optimal tracking-based algorithm for best arm identification.
Study online learning with off-policy feedback in adversarial bandit problems.
problem Learning with limited direct feedback in sequential decision making.
method Proposed algorithms that adapt pessimistic reward estimators to handle unknown behavior policy.
result Guaranteed regret bounds scaling with policy mismatch, improving performance against well-covered comparators.
Develops model selection for bandits balancing adversarial and stochastic guarantees.
problem Model selection in bandit scenarios with simultaneous adversarial and stochastic high-probability regret.
method Nested policy classes, balanced candidate regret bounds, mis-specification tests.
result Best of both world guarantees in linear bandits with simultaneous adversarial and stochastic environments.
New algorithms for efficient learning with partial information, reducing regret.
problem Online learning with partial observability and semi-bandit feedback.
method Implicit exploration strategy for near-optimal regret guarantees.
result First algorithms with near-optimal regret guarantees without knowing the observation system.
New strategies for identifying the best arm in bandits with decreasing variances.
problem Best arm identification in bandits with time-varying variances.
method Two policies: initial wait followed by continuous sampling, and periodic sampling with weighted average.
result Analytical guarantees and simulations show improved performance over existing methods.
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resourcescs.LG
A dueling bandit problem with resource constraints is solved using EXP3.
problem Maximizing rewards in dueling bandits with resource constraints.
method EXP3 algorithm considering resource consumptions.
result Achieves $ ilde{\mathcal{O}}\left({\frac{OPT^{(b)}}{B}}K^{1/3}T^{2/3}
ight)$ regret.
Proposes DEXP3.M for unknown delay in multi-arm bandit with multiple play.
problem Unknown delays in adversarial multi-armed bandit with multiple play.
method DEXP3.M algorithm addressing the challenge of associating feedback losses to arms.
result Regret bound is only slightly worse than single play setting.
Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries,…
Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unkn…
In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…
New study shows feedback doesn't improve MAB performance over erasure channels.
problem Distributed multi-armed bandit problem with arm erasure channels.
method Analyzed MAB with feedback and erasure channels, proving no improvement in regret.
result Regret lower bound of Ω(√KT + K / (1 - ε)) matches no-feedback upper bounds.
Algorithm reduces regret in non-stationary bandits and meta-learning with optimal arms.
problem Sequential decision-making with changing task boundaries and optimal arms.
method Reduction to bandit submodular maximization, meta-learning algorithms.
result Regret bounds for both non-stationary and bandit meta-learning problems.
In this paper we propose a novel framework for decentralized, online learning by many learners. At each moment of time, an instance characterized by a certain context may arrive to each learner; based on the context, the learner can select one of its own actions (which gives a reward and provides information) or reques…
Preselection Banditscs.LG
In this paper, we introduce the Preselection Bandit problem, in which the learner preselects a subset of arms (choice alternatives) for a user, which then chooses the final arm from this subset. The learner is not aware of the user's preferences, but can learn them from observed choices. In our concrete setting, we all…
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.
We introduce a stochastic contextual bandit model where at each time step the environment chooses a distribution over a context set and samples the context from this distribution. The learner observes only the context distribution while the exact context realization remains hidden. This allows for a broad range of appl…
New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.
problem Maximizing rewards while adhering to general long-term constraints.
method Weakly adaptive primal and dual regret minimizers.
result Achieves sublinear constraints violations and competitive ratios in both stochastic and adversarial settings.
Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.
New algorithm reduces clustering cost in bandit feedback.
problem Discovering hidden groupings in stochastic bandit feedback.
method ACB algorithm for active clustering with non-asymptotic lower bound.
result ACB algorithm's budget matches lower bound in most regimes.
Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…
We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its a…
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.
Improved Bandit PCA with optimal regret bound.
problem Minimizing regret in online PCA with bandit feedback.
method Combines online mirror descent and multiscale exploration.
result Minimax optimal regret bound of .
We introduce the safe linear stochastic bandit framework---a generalization of linear stochastic bandits---where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe) threshold with high probability. We assume that the learner initially has knowledg…
Algorithm minimizes regret in non-stationary dueling bandits with unknown parameters.
problem Minimizing regret in dueling bandits with time-varying preferences.
method Proposes Beat the Winner Reset algorithm and meta-algorithms DETECT and Monitored Dueling Bandits.
result Proves bounds on expected weak and strong regret for non-stationary dueling bandits.
A new algorithm for cryo-EM data collection that balances reward and latency.
problem Optimizing data collection in cryo-EM experiments with action delays.
method Latency-aware contextual bandit framework and COAF algorithm.
result The COAF algorithm efficiently maximizes reward over time in cryo-EM experiments.
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.
Algorithm for online decision making with unknown dynamics and aggregate feedback.
problem Online decision making with unknown dynamics and aggregate bandit feedback.
method Developed an algorithm based on online mirror descent with a self-concordant barrier regularization and an increasing learning rate schedule.
result Achieved regret for the online Markov Decision Process with episodes.
A new algorithm for resource-aware multi-armed bandits minimizes regret.
problem Optimizing resource usage in a multi-armed bandit problem with censored observations.
method UCB-inspired online learning algorithm with theoretical regret analysis.
result The proposed algorithm outperforms standard multi-armed bandit algorithms in simulations.
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.
A scheme robust to action erasures improves MAB performance.
problem Learning in multi-arm bandits with erasure channels.
method Proposes a scheme to work on top of any MAB algorithm.
result Worst-case regret is at most a factor of away from no-erasure case.
Safe Gaussian Process Bandit Optimization with sub-linear regret bounds.
problem Sequential decision-making under uncertainty and safety constraints.
method Developed SGP-UCB, a safe variant of GP-UCB with modifications to respect safety constraints.
result First sub-linear regret bounds for safe Gaussian Process Bandit Optimization.
Active learning method improves AI performance by balancing exploration and exploitation.
problem Efficiently acquiring samples for supervised learning in streaming data.
method Ensemble active learning by contextual bandits.
result Improved AI modeling performance through better sample acquisition.
Study shows how competition affects learning in matching markets, proving it's possible to balance stability, fairness, and regret.
problem How competition affects learning in matching markets and the impossibility of simultaneously guaranteeing stability and low optimal regret.
method Modeling a two-sided matching market with bandit learners and adding components of costs and transfers.
result It is possible to simultaneously guarantee stability, low optimal regret, fairness in the distribution of regret, and high social welfare.