Optimizes quadratic bandits with tight Hessian-dependent sample complexity bounds.
problem Understanding optimal sample complexity for quadratic functions.
method Introduces energy allocation and optimal energy spectrum to prove tight lower bounds. Solves for Hessian-independent optimal algorithm.
result Proves optimal Hessian-dependent sample complexities and existence of a universally optimal algorithm.
We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.…
New algorithm reduces regret in bandit optimization for high-dimensional data.
problem Optimizing decisions in uncertain environments with high-dimensional data.
method Inspired by online Newton step, proposes a simple and efficient BCO algorithm.
result Achieves optimal regret bounds for κ κ κ -convex functions. Quantum algorithms for multi-armed bandits are explored with limited reward access.
problem Exploring quantum speed-ups in multi-armed bandit problems with limited reward information.
method Introduced new bandit models and showed query complexity equivalence with classical algorithms.
result No quadratic speed-up is possible for multi-armed bandits with limited reward access.
In this paper, we propose the first computationally efficient projection-free algorithm for bandit convex optimization (BCO). We show that our algorithm achieves a sublinear regret of O ( n T 4 / 5 ) O(nT^{4/5}) O ( n T 4/5 ) (where T T T is the horizon and n n n is the dimension) for any bounded convex functions with uniformly bounded gradients. We …
Quantum algorithm solves best arm identification problem faster.
problem Identifying the best option in a set of choices.
method Quantum amplitude amplification algorithm.
result Quadratically faster than classical methods.
The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and performance upper bounds. However, much less is known about the inherent complexity …
SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.
problem Unbounded metric movement costs in bandit online convex optimization.
method SCaLE algorithm for high-dimensional dynamic quadratic hitting costs and ℓ 2 \ell_2 ℓ 2 -norm switching costs, with spectral regret analysis. result First algorithm achieving sub-linear dynamic regret without hitting cost knowledge.
RONM method reduces regret in stochastic convex bandits with decreasing noise.
problem Stochastic convex bandit problem with decreasing noise.
method Regularized Online Newton Method (RONM) based on Online Newton Method (ONM).
result RONM achieves polylogarithmic regret in time horizon n.
We study the problem of stochastic combinatorial pure exploration (CPE), where an agent sequentially pulls a set of single arms (a.k.a. a super arm) and tries to find the best super arm. Among a variety of problem settings of the CPE, we focus on the full-bandit setting, where we cannot observe the reward of each singl…
Study on information evolution in interactive decision making using multi-armed bandits.
problem Understanding information dynamics in interactive decision making.
method Stochastic multi-armed bandit problem, focusing on optimal arm with a fixed margin.
result Distinct growth phases in mutual information, showing decoupling between success probability and information gain.
New algorithms combat adversarial attacks in stochastic linear bandits.
problem Adversarial attacks on stochastic linear bandit rewards.
method Two variants of Robust Phased Elimination algorithms, one knowing C C C and one not. result Near-optimal regret in non-corrupted case and additive terms dependent on C C C . Optimal online learning algorithms for label-efficient prediction and bandits.
problem Efficient prediction in online learning with limited information.
method Optimistic online mirror descent with second order corrections and hybrid regularizers.
result Improved regret bounds for label-efficient prediction and bandits.
We provide new lower bounds on the regret that must be suffered by adversarial bandit algorithms. The new results show that recent upper bounds that either (a) hold with high-probability or (b) depend on the total lossof the best arm or (c) depend on the quadratic variation of the losses, are close to tight. Besides th…
We propose a contextual-bandit approach for demand side management by offering price incentives. More precisely, a target mean consumption is set at each round and the mean consumption is modeled as a complex function of the distribution of prices sent and of some contextual variables such as the temperature, weather, …
The paper considers the problem of global optimization in the setup of stochastic process bandits. We introduce an UCB algorithm which builds a cascade of discretization trees based on generic chaining in order to render possible his operability over a continuous domain. The theoretical framework applies to functions u…
Ensemble++ uses shared-factor ensembles to scale Thompson Sampling for linear and nonlinear bandits.
problem Computational challenges in Thompson Sampling for large-scale or non-conjugate settings.
method Ensemble++ with shared-factor architecture and random linear combinations.
result Ensemble++ achieves comparable regret to exact Thompson Sampling with significantly smaller ensemble sizes.
Improves reward bounds for prediction with expert advice using abstention.
problem Prediction with expert advice under bandit feedback with abstention.
method CBA algorithm exploiting abstention to improve reward bounds.
result Achieved significant improvement in reward bounds for general confidence-rated predictors.
CascadeBAI identifies best arms in cascading bandits with fixed confidence.
problem Finding the best set of items in cascading bandits with limited feedback.
method Developed CascadeBAI algorithm, derived upper and lower bounds on time complexity, introduced left-sided sub-Gaussian random variables.
result CascadeBAI is optimal in some practical regimes and performs well with limited feedback.
Quantum algorithms improve regret bounds for bandits with knapsacks.
problem Combining stochastic integer programming and online learning.
method Quantum algorithms for BwK with improved regret and time complexities.
result Quantum algorithms achieve better regret bounds than classical methods.
Optimal mixtures of generative models outperform individual models on image datasets.
problem Selecting the best single model from a group of trained generative models.
method Formulated a quadratic optimization problem and proposed the Mixture-UCB algorithm for efficient selection.
result Mixture of generative models achieves better evaluation scores than individual models on benchmark datasets.
New L2 regularization improves softmax MAB performance.
problem Improving softmax MAB performance with vanishing regularization.
method L2 regularization with vanishing parameter analyzed and proven convergent.
result Vanishing L2 regularization makes softmax MAB more numerically advantageous.
Paper introduces a new framework for optimizing non-convex functions.
problem Optimizing non-convex functions, especially DR-submodular and concave functions.
method Developed a general meta-algorithm to convert linear/quadratic optimization to optimization of upper-linearizable/quadratizable functions.
result Unified approach to concave and DR-submodular optimization problems.
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 algorithm tackles dynamic query routing to multiple embedding models.
problem Dynamic query routing to multiple embedding models under adversarial conditions.
method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.
result HPG algorithm achieves linearized policy regret of i l d e O ( s M T ) ilde{\mathcal O}(s\sqrt{M T}) i l d e O ( s M T ) . Develops new optimization techniques for decision-making under uncertainty.
problem Decision-making under uncertainty with complex cost functions and nested expectations.
method Introduces Multistage Conditional Compositional Optimization (MCCO) and develops multilevel Monte Carlo techniques.
result New optimization techniques reduce scenario complexity from exponential to polynomial growth.
New algorithm catches moving subspaces in bandit problems.
problem Adapt to changing low-dimensional latent subspaces in bandit settings.
method Piecewise-stationary low-rank linear contextual bandits with CUSUM-style boundary detection.
result Achieves intrinsic rank dynamic regret rate of O ( r T ) O(r\sqrt{T}) O ( r T ) . This work improves online regression and contextual bandits using neural networks.
problem Improving online regression and contextual bandits using neural networks.
method Investigates neural networks for online regression, showing O ( log T ) \mathcal{O}(\log T) O ( log T ) regret for almost convex losses and KL loss. result Shows i l d e O ( K L ∗ + K ) ilde{\mathcal{O}}(\sqrt{KL^*} + K) i l d e O ( K L ∗ + K ) regret for NeuCB, outperforming existing algorithms. New algorithm tackles nonstationary linear bandits with latent dynamics.
problem Nonstationary bandit problem with latent states and unknown dynamics.
method Explore-then-commit algorithm with exploration and commitment phases.
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. New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
Algorithm minimizes control regret for non-stationary LQR systems.
problem Control of non-stationary LQR systems with unknown dynamics.
method Adaptive non-stationarity detection and OLS estimator with small bias.
result Achieves optimal dynamic regret of $ ilde{\mathcal{O}}\left(V_T^{2/5}T^{3/5}
ight)$ .
We consider online learning for minimizing regret in unknown, episodic Markov decision processes (MDPs) with continuous states and actions. We develop variants of the UCRL and posterior sampling algorithms that employ nonparametric Gaussian process priors to generalize across the state and action spaces. When the trans…
Optimal algorithm for selecting high-quality arms from infinite bandit arms.
problem Efficiently choosing the best arm from an infinite set of options.
method Developed algorithms for both fixed confidence and fixed budget settings, achieving optimal or near-optimal sample complexities.
result Optimal sample complexity results for both fixed confidence and fixed budget settings, resolving open questions in the field.
We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of d d d -dimensional vectors in terms of a quadratic loss, while only having limited feedback about the environment's choices. We focus on a natural notion of bandit feedback where the learner only…
Adaptive linear bandit algorithm with best-of-three-worlds regret bounds.
problem Adaptive to adversarial and stochastic environments with varying sub-optimality gaps and corruption.
method Combines SCRiBLe algorithm with scaled-up sampling and optimistic online learning.
result Achieves best-of-three-worlds regret bounds of O ( T log T ) O(\sqrt{T \log T}) O ( T log T ) for adversarial and O ( log T Δ min + C log T Δ min ) O(\frac{\log T}{Δ_{\min}} + \sqrt{\frac{C \log T}{Δ_{\min}}}) O ( Δ m i n l o g T + Δ m i n C l o g T ) for stochastic environments. Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions d d d and i…
The trade-off between the cost of acquiring and processing data, and uncertainty due to a lack of data is fundamental in machine learning. A basic instance of this trade-off is the problem of deciding when to make noisy and costly observations of a discrete-time Gaussian random walk, so as to minimise the posterior var…
BanditPAM clusters data faster than traditional methods.
problem Efficiently clustering large datasets with arbitrary distance metrics.
method Inspired by multi-armed bandits, reduces PAM complexity from O ( n 2 ) O(n^2) O ( n 2 ) to O ( n log n ) O(n \log n) O ( n log n ) . result Matches state-of-the-art clustering loss with up to 4x faster results and 200x fewer distance computations.
New algorithms tackle RKHS bandits with reduced complexity and improved performance.
problem Adversarial and stochastic RKHS bandit problems with high computational complexity.
method Combining approximation theory with misspecified linear bandit methods.
result First general algorithm for adversarial RKHS bandit problem.
BestChanID identifies the channel with maximal capacity using training sequences.
problem Identifying the channel with maximal capacity among several discrete memoryless channels.
method Formulated as a multi-armed bandit problem, proposed a capacity estimator, and developed gap-elimination algorithms.
result Guaranteed to output the DMC with the largest capacity with a desired confidence.
Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
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 ( d T log T ) O(d\sqrt{T\log T}) O ( d T log T ) . 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.
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.
Unified approach for non-stationary and clustered bandits.
problem Solving non-stationary and clustered bandits with overlapping solutions.
method Test of homogeneity for seamless integration of non-stationary and clustered bandits.
result Unified solution framework for change detection and cluster identification.
A framework for auto-tuning hyper-parameters in contextual bandit algorithms.
problem Auto-tuning hyper-parameters in real-time for contextual bandit algorithms.
method Proposes a Syndicated Bandits framework to learn multiple hyper-parameters dynamically.
result Achieves optimal regret bounds under certain scenarios and handles multiple contextual bandit algorithms.
Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning algorithms may hijack their behavior, causing catastrophic loss in real-world appli…