New algorithm for context bandits with continuous actions.
problem Efficient decision-making with unknown action structures.
method Reduction-style algorithm combining supervised learning.
result Proven to work in general and validated with experiments.
Efficient algorithms for contextual bandits with smooth regret in continuous action spaces.
problem Efficient learning in large or continuous action spaces.
method Smooth regret notion and efficient algorithms for general function approximation.
result Statistically and computationally efficient algorithms for contextual bandits with smooth regret.
Paper solves Bayesian bandit problem with continuous-time limit and approximate policy.
problem Finding optimal policy in Bayesian bandit problems with large horizons.
method Reformulates Bayesian bandit problem as continuous Hamilton-Jacobi-Bellman (HJB) equation and proposes approximate Bayes-optimal policy.
result Approximate Bayes-optimal policy for large horizons with constant computational cost.
In this paper, we propose three online algorithms for submodular maximisation. The first one, Mono-Frank-Wolfe, reduces the number of per-function gradient evaluations from T 1 / 2 T^{1/2} T 1/2 [Chen2018Online] and T 3 / 2 T^{3/2} T 3/2 [chen2018projection] to 1, and achieves a ( 1 − 1 / e ) (1-1/e) ( 1 − 1/ e ) -regret bound of O ( T 4 / 5 ) O(T^{4/5}) O ( T 4/5 ) . The second one, Bandit-F…
A new framework tunes hyperparameters in real-time for contextual bandits.
problem Optimizing hyperparameters for contextual bandits in real-time.
method CDT (Continuous Dynamic Tuning) framework using Zooming TS algorithm.
result Achieves sublinear regret and performs better than existing methods.
New algorithm optimizes smooth functions with Hölder exponent > 1.
problem Optimizing smooth functions with unknown Hölder exponent > 1.
method Two-layer algorithms using misspecified linear/polynomial bandit algorithms in bins.
result Regret bound of O ~ ( T d + α d + 2 α ) \tilde{O}(T^{\frac{d+\alpha}{d+2\alpha}}) O ~ ( T d + 2 α d + α ) for α > 1 \alpha > 1 α > 1 . Transfer learning for bandits with latent Lipschitz continuity.
problem Learning to transfer structural information from prior tasks to new tasks.
method Proposes a framework to estimate Lipschitz constant from prior tasks and apply it to new tasks.
result Regret bound close to oracle algorithm with full knowledge of Lipschitz constant under mild assumptions.
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and …
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}) O ∗ ( T ) cumulative regret. The paper tackles minimax optimality in continuum contextual bandits with Hölder continuity.
problem Minimizing regret in a continuum of contexts with Hölder continuity.
method Proves a static-to-contextual regret conversion theorem and analyzes various dependency cases.
result Achieves minimax optimal contextual regret for convex and strongly convex bandits.
We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…
Book covers tools for zeroth-order convex optimisation.
problem Zeroth-order convex optimisation.
method Cutting plane methods, interior point methods, continuous exponential weights, gradient descent, online Newton step.
result Improved existing bounds and algorithms.
Study of bandit problem with Poisson decision times and Lévy processes.
problem Continuous-time multi-armed bandit problem with Poisson decision times.
method Gittins index policy applied to spectrally one-sided Lévy processes.
result Gittins index converges to classical Lévy bandit index.
ArtificialReplay improves data efficiency in bandits using historical data.
problem Data inefficiency in warm-starting bandit algorithms.
method ArtificialReplay, a meta-algorithm for incorporating historical data into any bandit algorithm.
result ArtificialReplay uses only a fraction of historical data compared to a full warm-start approach, achieving identical regret.
This paper unifies risk-averse Thompson sampling for continuous risk functionals.
problem Designing and analyzing risk-averse Thompson sampling algorithms for continuous risk functionals.
method Developed analytical toolkits to prove asymptotically optimal regret bounds for various risk measures.
result Proved asymptotic optimality of ρ ρ ρ -MTS for Bernoulli distributions and a class of risk measures. The paper extends Thompson Sampling to infinite action spaces using information theory.
problem Addressing the limitation of finite action spaces in Thompson Sampling.
method Information-theoretic analysis, extending rate-distortion theory to infinite action spaces.
result Derives a near-optimal regret bound for bandits with infinite and continuous action spaces.
Practical algorithm for contextual bandits with large action spaces.
problem Efficient algorithms for decision making in large, continuous action spaces.
method Uses computational oracles for supervised learning and optimization over the action space.
result Achieves sample complexity, runtime, and memory independent of the size of the action space.
Paper analyzes nonconvex bandit problems with improved adaptive methods.
problem Continuous armed bandit problems for nonconvex cost functions.
method Simple and adaptive bin splitting methods.
result Adaptive method achieves locally minimax optimal expected cumulative regret.
Study on policy gradient for stochastic bandits using diffusion approximation.
problem Improving policy gradient methods for stochastic bandits with optimal regret bounds.
method Continuous-time diffusion approximation of policy gradient with learning rate analysis.
result Proved optimal regret bound of O ( k log ( k ) log ( n ) / η ) O(k \log(k) \log(n) / η) O ( k log ( k ) log ( n ) / η ) for η = O ( Δ 2 / log ( n ) ) η= O(Δ^2/\log(n)) η = O ( Δ 2 / log ( n )) . The paper tackles lifelong learning in multi-armed bandits, aiming to minimize average regret over multiple tasks.
problem Minimizing average regret in multi-armed bandits over multiple tasks.
method Confidence interval tuning of UCB algorithms and greedy algorithms applied to a bandit over bandit approach.
result Empirical improvement over previous work in the mortal bandit problem.
The paper tackles online learning problems with monotone arm sequences, achieving optimal or near-optimal regret bounds.
problem Online learning problems with ordinal and monotone arm sequences, such as dynamic pricing and clinical trials.
method Proposes algorithms for continuum-armed bandit problems with monotone arm sequences, achieving optimal or near-optimal regret bounds.
result Achieves optimal or near-optimal regret bounds for monotone arm sequences, differing from the continuous-armed bandit literature.
We describe a novel algorithm for noisy global optimisation and continuum-armed bandits, with good convergence properties over any continuous reward function having finitely many polynomial maxima. Over such functions, our algorithm achieves square-root regret in bandits, and inverse-square-root error in optimisation, …
New framework tackles submodular welfare with multi-agent combinatorial bandits.
problem Maximizing total welfare among agents with shared constraints and submodular utilities under bandit feedback.
method Proposes an explore-then-commit strategy with randomized assignments for multi-agent combinatorial bandits.
result Achieves i l d e O ( T 2 / 3 ) ilde{\mathcal{O}}(T^{2/3}) i l d e O ( T 2/3 ) regret, first for partition-based submodular welfare problem under bandit feedback. New algorithms improve contextual bandits with neural networks and energy models.
problem Inefficient exploration in non-linear models for contextual bandits.
method Maximum entropy exploration using neural networks and energy models.
result Both techniques outperform standard algorithms, with energy models best overall.
The paper tightens the regret rate for linear bandit problems.
problem Bayesian regret in linear bandit problems.
method Information-theoretic framework and chaining argument.
result Established a new bound with a tight rate of O ( d T ) O(d\sqrt{T}) O ( d T ) . BLiE optimizes hyperparameters with theoretical guarantees and superior performance.
problem Hyperparameter optimization in machine learning.
method Lipschitz bandit approach exploiting Lipschitz continuity.
result BLiE finds ε-optimal hyperparameters with theoretical complexity.
Study examines impact of missing data on multi-armed bandit algorithms.
problem Impact of missing data on performance of multi-armed bandit algorithms.
method Extensive simulation study of two-armed bandit algorithms with binary outcomes, considering different probabilities of missingness.
result Impact on performance varies depending on the balance between exploration and exploitation.
We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). This algorithm is based on Gated Linear Networks (GLNs), a recently introduced deep learning architecture with properties well-suited to the online setting. Leveraging data-dependent gating properties of …
Nonparametric Thompson Sampling achieves optimal regret for risk-averse bandits with sub-Gaussian rewards.
problem Optimizing risk-averse bandit problems with sub-Gaussian rewards.
method Anchor-free nonparametric Thompson Sampling algorithm ρ e x t − N P T S S G ρ ext{-}NPTS_{\mathrm{SG}} ρ e x t − N P T S SG . result Achieves regret matching the instance-dependent lower bound to leading order in log n \log n log n . The paper provides robustness guarantees for mode estimation in bandits.
problem Understanding robustness in mode estimation under adversarial data contamination.
method Simple randomization and theoretical analysis of multi-armed bandits.
result Regret guarantees for various modal bandit problems.
Paper tackles robust batched bandits for heavy-tailed rewards.
problem Clinical trials and other applications with heavy-tailed rewards.
method Proposes robust batched bandit algorithms for heavy-tailed rewards in finite-arm and Lipschitz-continuous settings.
result Heavier-tailed rewards require fewer batches for near-optimal regret in the instance-independent regime and Lipschitz setting.
A new algorithm for CTMAB minimizes regret with sampling costs.
problem Continuous-time multi-arm bandit problem with sampling costs.
method Established lower bounds and proposed algorithms to minimize regret.
result Achieved lower bounds on regret up to logarithmic factors.
Unified framework for risk-aware policy learning in contextual bandits.
problem Optimizing decision rules in high-stakes domains with adverse outcomes.
method Distributional framework for Lipschitz-continuous risk functionals, with novel empirical concentration inequalities.
result Data-dependent suboptimality bounds with an i l d e O ( 1 / n ) ilde{\mathcal{O}}(1/\sqrt{n}) i l d e O ( 1/ n ) rate, matching risk-neutral offline policy optimization. Study incentivizes exploration in non-stationary MAB with compensation.
problem Incentivized exploration for non-stationary stochastic bandits with biased feedback.
method Proposed algorithms for abruptly-changing and continuously-changing non-stationary environments.
result Achieves sublinear regret and compensation over time.
New algorithms improve decision-making with limited offline data.
problem Using limited offline data to cluster users for better decision-making.
method Proposed two algorithms: Off-C2LUB and Off-CLUB to address data insufficiency.
result Both algorithms outperform existing methods under limited offline user data.
ES reduces high-probability regret in stochastic linear bandits.
problem High-probability regret in stochastic linear bandits.
method Linear ensemble sampling with standard Gaussian perturbations, analyzing m = Θ ( d log n ) m=Θ(d\log n) m = Θ ( d log n ) ensemble size. result ES achieves i l d e O ( d 3 / 2 n ) ilde O(d^{3/2}\sqrt n) i l d e O ( d 3/2 n ) high-probability regret, closing the gap to Thompson sampling. Unified analysis of kernel-based and locally adaptive bandit optimization methods.
problem Performance of bandit optimization algorithms in RKHS functions.
method Investigates the relationship between kernel regularity and algorithmic performance, characterizing spectral properties of various kernels.
result Unified framework for analyzing kernel-based and locally adaptive bandit algorithms, deriving explicit regret bounds.
New algorithms boost SAT solver performance by optimizing restart strategies.
problem Optimizing decision-making under time constraints with restarts.
method Developed online learning algorithms for a bandit problem with controlled restarts.
result Achieved O ( log ( τ ) ) O(\log(τ)) O ( log ( τ )) and O ( τ log ( τ ) ) O(\sqrt{τ\log(τ)}) O ( τ log ( τ ) ) regret bounds. New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.
problem Adversarial corruption in Lipschitz bandits.
method Developed robust Lipschitz bandit algorithms for weak and strong adversaries.
result Achieved sub-linear regret under both weak and strong adversaries.
We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact optimization oracle but does not know the expected base arm outcomes beforehand. When th…
New algorithm achieves consistent learning from context in bandit problems.
problem Learning from context in bandit problems with non-i.i.d. contexts.
method Optimistically universal learning rule balancing generalization and personalization.
result Achieves universal consistency for large classes of non-i.i.d. contexts.
Paper proposes a risk-aware decision-making framework for real-world sequential decisions.
problem Real-world sequential decision-making problems often have critical constraints that learning solutions often neglect.
method Actor multi-critic architecture with risk characterization.
result Our approach consistently satisfies system constraints with minimal performance toll.
This paper proposes a general framework of multi-armed bandit (MAB) processes by introducing a type of restrictions on the switches among arms evolving in continuous time. The Gittins index process is constructed for any single arm subject to the restrictions on switches and then the optimality of the corresponding Git…
New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
problem Delayed feedback in Lipschitz bandits.
method Design of algorithms for bounded and unbounded stochastic delays.
result Sublinear regret guarantees for both bounded and unbounded delays.
This paper uses bandit algorithms to reduce the cost of user interface experimentation in online retail.
problem Reducing the cost of user interface experimentation in online retail.
method Modeling user interface experimentation as an opportunistic bandit problem, reducing the cost of exploration.
result Significant regret reduction and improved contextual information for testing.
Optimal best-arm identification in linear bandits reduces sampling budget.
problem Identifying the best arm with fixed confidence in stochastic linear bandits.
method A simple algorithm that tracks an optimal proportion of arm draws, updated as rarely as desired.
result The algorithm's sampling complexity matches known lower bounds, asymptotically almost surely and in expectation.
This paper studies continuum-armed bandits under Besov smoothness conditions and derives minimax rates.
problem Optimizing an unknown function with limited evaluations.
method Studies continuum-armed bandits under Besov smoothness conditions and derives minimax rates.
result Minimax rates over Besov spaces are identical to those over the smallest Hölder space into which Besov spaces embed.