Balances the regret of different algorithms in bandit and RL problems.
problem Model selection in bandit and reinforcement learning.
method Estimates and balances the empirical regrets of algorithms.
result Achieves near-optimal regret compared to the optimal base algorithm.
IDS improves sparse linear bandits by balancing information and regret.
problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.
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.
Balances and eliminates base algorithms in bandits and RL to bound total regret.
problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.
We study Smoothed Online Convex Optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a Ω ( d ) Ω(\sqrt{d}) Ω ( d ) lower bound on the competitive ratio of any online algorithm, where d d d is the dimension of the action space, we ask under what conditio…
New algorithm balances personalization and statistical validity in MRTs.
problem Optimizing decisions in nonstationary settings with habituation and recovery.
method ROGUE-TS Thompson Sampling with probability clipping.
result Achieves lower regret and maintains high statistical power.
New insights into balancing reward and fairness in stochastic MAB.
problem Balancing reward and fairness in stochastic multi-armed bandits.
method Formulated a penalization framework and proposed a hard-threshold UCB-like algorithm.
result Asymptotic fairness, nearly optimal regret, better reward-fairness tradeoff.
LAFF algorithm balances adaptability and non-exploitability in repeated games.
problem Low regret in repeated games against unknown opponent classes.
method LAFF algorithm searches within sub-algorithms optimal for each opponent class and uses a punishment policy for exploitation.
result LAFF guarantees sublinear regret uniformly over possible opponents, except exploitative ones, for which it guarantees linear regret.
New bounds on IDS for RL show how to balance computation and learning efficiency.
problem Understanding and optimizing information-directed sampling (IDS) for reinforcement learning.
method Developed novel information-theoretic tools to bound information ratio and cumulative information gain.
result Derived prior-free Bayesian regret bounds for IDS in tabular finite-horizon MDPs and improved computational efficiency.
Algorithm balances online and offline data for linear bandits.
problem Online learning with an offline dataset in linear bandits.
method Proposes a linear bandit algorithm that uses offline data early and increasingly favors exploration as the horizon grows.
result Establishes regret bounds showing competitive performance with both purely online and offline solutions.
This paper optimizes revenue and resource balance in network revenue management.
problem Maximizing revenue while ensuring fair resource consumption across different suppliers.
method Introduces a regularized revenue objective and a primal-dual UCB algorithm for continuous prices and balancing.
result Achieves a worst-case regret of O ~ ( N 5 / 2 T ) \widetilde O(N^{5/2}\sqrt{T}) O ( N 5/2 T ) for revenue maximization and balancing. New bounds for high-dimensional sparse linear bandits, balancing information and regret.
problem Stochastic linear bandits with high-dimensional sparse features.
method Derivation of minimax regret lower and upper bounds for explore-then-commit algorithm.
result Optimal rate of Θ ( n 2 / 3 ) Θ(n^{2/3}) Θ ( n 2/3 ) for data-poor regime, complemented by O ( n ) O(\sqrt{n}) O ( n ) under signal magnitude assumption. New algorithm balances exploration cost between groups in multi-armed bandits.
problem Balancing exploration cost between groups in multi-armed bandits.
method Introducing Col-UCB algorithm that dynamically coordinates exploration across groups.
result Achieves optimal minimax and instance-dependent collaborative regret up to logarithmic factors.
Improved algorithm reduces regret in NRM with unknown demand.
problem Optimizing prices for products with limited resources under unknown demand.
method Primal-dual optimization with demand balancing.
result Improved regret bound of O ( N 3.25 T ) O(N^{3.25}\sqrt{T}) O ( N 3.25 T ) . Algorithm balances learning and coverage for multi-robots over unknown fields.
problem Balancing learning and coverage for multi-robots over unknown, nonuniform sensory fields.
method DSLC algorithm that schedules learning and coverage epochs, using Gaussian Process modeling and coverage regret analysis.
result Upper bound on expected cumulative coverage regret provided for DSLC.
This work improves privacy in federated combinatorial bandits by balancing regret and privacy.
problem Privacy-preserving learning in competitive online learning settings with quality constraints.
method Proposes P-FCB algorithm for federated combinatorial bandits, balancing regret and privacy.
result Improves regret while maintaining quality constraints and privacy guarantees.
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.
A new algorithm balances exploration and exploitation in online decision-making.
problem Balancing exploration and exploitation in online decision-making.
method Proposed C 4 C^4 C 4 -UCB algorithm incorporating conservative mechanism. result Proved n-step upper regret bound for two situations.
The problem of bipartite ranking, where instances are labeled positive or negative and the goal is to learn a scoring function that minimizes the probability of mis-ranking a pair of positive and negative instances (or equivalently, that maximizes the area under the ROC curve), has been widely studied in recent years. …
New algorithm reduces regret bounds for Bayesian optimization with unknown hyperparameters.
problem Optimizing black-box functions with unknown hyperparameters, especially length scale.
method Length Scale Balancing (LB) - aggregating multiple surrogate models with varying length scales.
result LB achieves a regret bound only logaritically away from the oracle algorithm.
Optimizes regret distribution in stochastic bandits for risk balance.
problem Balancing regret expectation and tail risk in stochastic bandits.
method Characterizes optimal regret tail probability for any threshold, proposes new policies.
result Discovers an intrinsic gap in optimal tail rate based on time horizon uncertainty.
Kernel-UCBVI algorithm balances exploration and exploitation in metric state-action spaces.
problem Exploration-exploitation dilemma in finite-horizon reinforcement learning with metric state-action spaces.
method Kernel-UCBVI, leveraging smoothness and kernel estimators of rewards and transitions.
result First regret bound for kernel-based RL using smoothing kernels, O ( H 3 K 2 d / ( 2 d + 1 ) ) O(H^3 K^{2d/(2d+1)}) O ( H 3 K 2 d / ( 2 d + 1 ) ) . New algorithms balance collaboration and adversarial behavior in linear bandits.
problem Minimizing regret in a collaborative linear bandit problem with adversarial agents.
method Robust collaborative phased elimination algorithm with tight analyses.
result Achieves near-optimal regret bounds of $O\left(α+ 1/\sqrt{M}
ight) \sqrt{dT}$ for good agents.
Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We study a consideration for the expl…
A new federated multi-armed bandit framework with personalization balances generalization and personalization.
problem Balancing generalization and personalization in federated multi-armed bandits.
method Proposed a Personalized Federated Upper Confidence Bound (PF-UCB) algorithm to achieve a O ( log ( T ) ) O(\log(T)) O ( log ( T )) regret. result PF-UCB achieves an O ( log ( T ) ) O(\log(T)) O ( log ( T )) regret regardless of personalization degree and has similar instance dependency to lower bound. BaNk-UCB tackles batched nonparametric bandits with k-NN regression and UCB.
problem Sequential decision-making with limited online feedback in domains like medicine and marketing.
method Combines k-NN regression with UCB principle for fully nonparametric, adaptive, and simple implementation.
result Near-optimal regret guarantees under Lipschitz smoothness and margin assumptions, with minimax-optimal rates.
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.
Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We develop algorithms for contextual …
Paper solves learning imperfect-information games with fewer episodes.
problem Learning imperfect-information extensive-form games from bandit feedback.
method Balanced Online Mirror Descent and Balanced Counterfactual Regret Minimization algorithms.
result Achieves near-optimal sample complexity for finding approximate Nash equilibria.
Protocol learns pure quantum states with minimal disturbance.
problem Efficiently learn quantum states with minimal disturbance.
method Sequential measurements with minimal disturbance.
result Achieves maximal precision with polylogarithmic regret.
This paper balances short-term and long-term rewards in policy learning.
problem Balancing short-term and long-term rewards in policy learning.
method Formalizes a new framework to balance rewards, identifies rewards under mild assumptions, deduces efficiency bounds, and develops a policy learning approach.
result The proposed method improves the estimator of long-term reward and reduces regret.
New algorithm prevents strategic replication in multi-armed bandit problems.
problem Strategic replication by agents can exploit bandit algorithms' balance.
method Designs Hierarchical UCB (H-UCB) and Robust Hierarchical UCB (RH-UCB) algorithms.
result Achieves O ( ln T ) O(\ln T) O ( ln T ) -regret and sublinear regret in realistic scenarios. Paper presents an algorithm for optimal regret in communicating Markov decision processes.
problem Achieving optimal regret in Markov decision processes with a communicating assumption.
method The algorithm explicitly tracks the constant K(M) to learn optimally, balancing exploration, co-exploration, and exploitation.
result The algorithm achieves asymptotically optimal regret K ( M ) log ( T ) + o ( log ( T ) ) K(M) \log(T) + \mathrm{o}(\log(T)) K ( M ) log ( T ) + o ( log ( T )) for communicating Markov decision processes. Optimizes assortment decisions with a new OFU scheme for online choice problems.
problem Online assortment optimization under stochastic choice with revenue performance and inference quality considerations.
method Forced-exploration OFU scheme combining regularized estimators for decision making and inference.
result Explicit regret bound and error bounds for approximate optimistic actions, showing Pareto optimality.
The paper studies MAB problems with LDP to balance privacy and service quality.
problem Balancing privacy and service quality in multi-armed bandit systems.
method Investigates regret minimization for MAB with LDP guarantee, proving lower bounds and proposing matching upper bounds algorithms.
result Regret upper bounds match lower bounds up to constant factors for MAB algorithms with LDP guarantee.
The paper analyzes regret in bilateral trade mechanisms without prior valuations.
problem Designing efficient trade mechanisms without prior knowledge of valuations.
method Regret minimization framework over rounds of interactions with no prior knowledge of valuations.
result Characterization of regret bounds for different feedback models and valuations.
OE2D framework reduces contextual bandits to offline regression for near-optimal regret.
problem Efficiently learning contextual bandits with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that reduces contextual bandits to offline regression.
result Near-optimal regret for contextual bandits with large action spaces and O ( log T ) O(\log T) O ( log T ) calls to an offline regression oracle. ALEXP improves model selection in linear bandits with exponential regret improvement.
problem Model selection in linear bandits is challenging due to balancing exploration and exploitation.
method ALEXP uses online learning with favorable bias-variance trade-off to emulate full-information feedback.
result ALEXP achieves an exponentially improved ( log M \log M log M ) regret dependence on the number of models M M M . 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.
Proposes PE-GP-UCB for time-varying Bayesian optimisation.
problem Time-varying Gaussian process bandits with unknown prior.
method PE-GP-UCB algorithm, relying on consistency of function values with priors.
result Regret bound provided for the proposed algorithm.
Algorithm minimizes regret while adhering to unknown safety constraints.
problem Online learning with unknown safety constraints.
method General meta-algorithm leveraging online regression and learning oracles.
result Concrete algorithm with T \sqrt{T} T regret for linear constraints. We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.
problem Learning equilibrium in leader-follower games with noisy bandit feedback.
method Proposed Correlated Stackelberg Equilibrium (CSE) and online learning algorithms balancing exploration and exploitation.
result Achieves no-external Stackelberg-regret, converging to approximate CSE.
New algorithm reduces online decision-making regret with efficient LP re-solving and parallel first-order method.
problem Worse regret guarantees and high computational cost of LP-based OLP algorithms.
method Combines LP-based and first-order OLP methods, re-solving LP subproblems periodically and using parallel first-order method.
result Achieves O ( log ( T / f ) + f ) \mathscr{O}(\log (T/f) + \sqrt{f}) O ( log ( T / f ) + f ) regret, balancing computational efficiency and superior regret guarantee. Neural- σ 2 σ^2 σ 2 -LinearUCB improves regret in neural contextual bandits.
problem Balancing exploration and exploitation in neural contextual bandits.
method Proposes a variance-aware neural UCB algorithm using neural representations and an upper bound of reward noise variance.
result Oracle and practical versions of Neural- σ 2 σ^2 σ 2 -LinearUCB achieve better regret guarantees and performance. 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…
Algorithm optimizes two objectives in bandits: minimizing regret and identifying best arm.
problem Balancing exploration and exploitation for optimal performance in multi-armed bandits.
method Design and analysis of BoBW-lil'UCB ( γ ) (γ) ( γ ) algorithm, establishing lower bounds. result BoBW-lil'UCB ( γ ) (γ) ( γ ) achieves optimal performance for RM or BAI under different γ γ γ values. Algorithm adapts to shifting domains with minimal label queries.
problem Adaptive learning in online machine learning systems with domain shifts.
method Adaptive algorithm balancing regret and label queries for hidden domains.
result Achieves lower regret compared to uniform and greedy queries.
In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptim…