Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.
problem Efficient optimisation of expensive black-box functions in unknown search spaces.
method Expands search space over iterations based on a hyperharmonic series, scales to high dimensions.
result Sub-linear regret growth for both algorithms.
Kernel ε ε ε -Greedy optimizes multi-armed bandits with covariates for sub-linear regret.
problem Optimizing multi-armed bandits with covariates in a reproducing kernel Hilbert space.
method Online weighted kernel ridge regression estimator for mean reward function estimation.
result Achieves sub-linear regret rate and optimal T \sqrt{T} T regret rate under margin condition. In this paper, we introduce Ballooning Multi-Armed Bandits (BL-MAB), a novel extension of the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (or balloons) over time. In contrast to the classical MAB setting where the regret is computed with respect to the best arm overall, the regr…
In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property. Specifically, a sequence of monotone DR-submodular objective functions $\{f_t(x)\}_{t=1…
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.
First robust bandit algorithm for contextual bandits with sub-linear regret.
problem Vulnerability of linear contextual bandit algorithms to adversarial attacks.
method Proposes a robust bandit algorithm for stochastic linear contextual bandits under fully adaptive and omniscient attacks.
result Sub-linear regret under various attacks without requiring attack information.
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.
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.
This paper addresses robust CBs for linear SEMs with model fluctuations.
problem Designing interventions in causal systems with linear SEMs that are robust to model fluctuations.
method Develops a robust CB algorithm and analyzes its regret under model deviation.
result The proposed algorithm achieves nearly optimal i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) regret when C C C is o ( T ) o(\sqrt{T}) o ( T ) and maintains sub-linear regret for a broader range of C C C . In this paper, we consider the problem of preserving privacy in the online learning setting. We study the problem in the online convex programming (OCP) framework---a popular online learning setting with several interesting theoretical and practical implications---while using differential privacy as the formal privacy …
New algorithms reduce slate bandit regret for large slates, outperforming existing methods.
problem Non-separable reward functions in slate bandits with many slates.
method Design of algorithms with sub-linear regret.
result Sub-linear regret with respect to the time horizon for large number of slates.
New algorithms for planning with adversarial changes in costs.
problem Planning with adversarial changes in costs over time.
method Developed algorithms for adversarial SSP with high probability regret bounds.
result Obtained sub-linear regret bounds for adversarial SSP.
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.
Paper tackles domain adaptation for contextual bandits with sub-linear regret.
problem Adapting contextual bandit algorithms across domains with distribution shift.
method Learn a bandit model for the target domain using feedback from the source domain.
result Sub-linear regret bound maintained across domains.
In X \mathcal{X} X -armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, su…
We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static adversarial regret, whose comparator is the optimal fixed action in hindsight. However, static regret is not an appropriate metric when the un…
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.
COBRA addresses strategic behavior in online platforms by ensuring truthful reporting without monetary incentives.
problem Ensuring truthful reporting from strategic agents in online platforms.
method Proposes COBRA, an algorithm for contextual bandits involving strategic agents that disincentivizes strategic behavior.
result COBRA achieves sub-linear regret guarantee and incentive compatibility without monetary incentives.
Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.
problem Designing incentives for large populations of agents in MFGs with uncertain model details.
method Developed optimistic exploration algorithms for agents with no-adaptive regret behaviors.
result Sub-linear regret guarantees for cumulative gaps between agent behaviors and desired outcomes.
We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high…
New algorithm reduces risk in online games with limited feedback.
problem Risk-averse learning in repeated unknown games with bandit feedback.
method Proposes a momentum-based algorithm to estimate CVaR using historical cost values.
result Achieves sub-linear regret and outperforms existing methods in numerical experiments.
A multi-user multi-armed bandit (MAB) framework is used to develop algorithms for uncoordinated spectrum access. The number of users is assumed to be unknown to each user. A stochastic setting is first considered, where the rewards on a channel are the same for each user. In contrast to prior work, it is assumed that t…
A new algorithm improves stochastic linear bandit performance using residual bootstrap.
problem Improving performance in stochastic linear bandit problems.
method Residual bootstrap exploration to estimate mean reward and pull the arm with the highest estimate.
result Proposed algorithm exttt{LinReBoot} achieves high-probability sub-linear regret under mild conditions.
In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinfo…
New algorithms for fair item allocation with limited copies.
problem Fair division of numerous items with few copies.
method Modeling as a contextual bandit problem with sub-linear regret guarantees.
result Proposed algorithms achieve sub-linear regret in fair item allocation.
Develops algorithms for CCBs with non-linear costs, improving safety and performance.
problem Safety constraints in sequential decision making with non-linear arm costs.
method Innovative algorithms using Inverse Gap Weighting (IGW) and online regression oracle.
result Sub-linear regret bounds for C-SquareCB and first-order regret for C-FastCB.
Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationar…
Algorithm optimizes spectrum access for dynamic multi-user environments.
problem Optimizing spectrum access in uncoordinated multi-user environments with potential collisions.
method Stochastic multi-user bandit framework with estimation and allocation phases.
result Order-optimal system-wide regret of O ( log T ) O(\log T) O ( log T ) for dynamic and static cases. Algorithm learns optimal arm selection in unsupervised sequential selection with contextual information.
problem Learning optimal arm selection in unsupervised sequential selection with contextual information.
method Proposes an algorithm for the contextual USS problem under the CWD property, demonstrating sub-linear regret.
result Demonstrates sub-linear regret for the proposed algorithm.
New algorithm reduces regret in CBs with time-varying models.
problem Designing robust interventions in CBs with unknown, fluctuating causal models.
method Proposes a robust CB algorithm with upper and lower bounds on regret.
result Achieves nearly optimal i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) regret under certain conditions. We investigate the use of bootstrapping in the bandit setting. We first show that the commonly used non-parametric bootstrapping (NPB) procedure can be provably inefficient and establish a near-linear lower bound on the regret incurred by it under the bandit model with Bernoulli rewards. We show that NPB with an approp…
This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.
problem Theoretical confidence parameter in GP-UCB increases with iterations, leading to large values.
method Introduced IRGP-UCB, a randomized variant of GP-UCB using a shifted exponential distribution for confidence parameters.
result IRGP-UCB achieves sub-linear regret without increasing the confidence parameter.
A new algorithm for restless bandits handles long-range dependencies.
problem Generalization of linear bandits with time-dependent parameters.
method LinMix-UCB algorithm with Berbee's coupling lemma.
result Sub-linear regret of $\mathcal{O}\left(\sqrt{d n\mathrm{polylog}(n) }
ight)$ .
New algorithm SELECT minimizes satisficing regret in bandits.
problem Minimizing regret in bandit optimization with satisficing arms.
method SELECT algorithm for satisficing regret minimization.
result SELECT achieves constant expected satisficing regret.
New algorithms improve online prediction from experts with privacy constraints.
problem Online prediction from experts under privacy constraints.
method Proposed and analyzed new algorithms for approximate and pure differential privacy.
result Achieved improved regret bounds for various adversaries.
Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a sub-linear, O ( T log T ) O(\sqrt{T}\log T) O ( T log T ) , regret bound for a variant of Thompson sampling. Our…
EBUCB framework achieves optimal regret with bounded approximate inference error.
problem Theoretical gap between practical performance and theoretical justification of Bayesian bandit algorithms with approximate inference.
method Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that accommodates bandit problems with approximate inference.
result EBUCB achieves optimal regret order O ( log T ) O(\log T) O ( log T ) under certain conditions on inference error. New RL algorithm optimizes policies with bandit feedback, matching previous bounds.
problem Optimizing policies with unknown transitions and bandit feedback.
method Optimistic Trust Region Policy Optimization (TRPO) algorithm.
result Sub-linear regret bounds for both stochastic and adversarial rewards.
Algorithm reduces long-term policy regret in ML decision-making.
problem Capturing long-term impacts of ML decisions in communities.
method Modeling communities as arms in a multi-armed bandit problem, defining policy regret as a stronger metric than external regret.
result Algorithm achieves provably sub-linear policy regret for long time horizons.
We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the d…
LNUCB-TA improves MAB performance by dynamically adjusting exploration rates and recognizing spatiotemporal patterns.
problem Suboptimal performance in environments with rapidly changing reward structures and static exploration rates.
method Hybrid model combining linear and nonlinear estimation, with adaptive k-NN for temporal attention.
result Significantly outperforms state-of-the-art algorithms in cumulative and mean reward, convergence, and robustness.
Algorithm finds optimal regularizers for online linear optimization.
problem Finding optimal regularizers to minimize regret in online linear optimization.
method Algorithm takes input sets and outputs an optimal regularizer for FTRL.
result Algorithm guarantees regret within a constant factor of the best possible learning algorithm.
Paper develops a robust Bayesian optimization method for noisy zeroth-order settings.
problem Achieving robustness to distributional shift in machine learning.
method Distributionally robust Bayesian optimization (DRBO) algorithm for noisy zeroth-order optimization.
result DRBO algorithm provably obtains sub-linear robust regret in various settings.
Study online learning with individual fairness without known similarity measure.
problem Online learning with individual fairness constraints without a known similarity measure.
method Reduction to standard online classification, leveraging auditor feedback.
result Achieves sub-linear regret and fairness violations with stochastic data.
Avare improves optimization and sampling with adaptive importance sampling.
problem Improving convergence rate of stochastic gradient-based algorithms.
method Adaptive importance sampling with decreasing step-sizes.
result Achieves dynamic regret bounds of O ( T 2 / 3 ) \mathcal{O}(T^{2/3}) O ( T 2/3 ) and O ( T 5 / 6 ) \mathcal{O}(T^{5/6}) O ( T 5/6 ) . New algorithm for online learning in episodic MDPs with convex objectives.
problem Online episodic convex reinforcement learning.
method Online mirror descent algorithm with varying constraint sets and exploration bonus.
result Near-optimal regret bounds for online CURL without prior knowledge of transition function.
New algorithm reduces learning regret in multi-agent systems with unknown dynamics.
problem Challenges in decentralized learning due to unknown dynamics and lack of communication.
method Proposed MARL algorithm for two-agent LQ systems with unknown dynamics and one-directional communication.
result Achieved O ( T ) O(\sqrt{T}) O ( T ) regret bound for multi-agent LQ systems with certain communication patterns. Study contextual online pricing with biased offline data, achieving optimal regret bounds.
problem Contextual online pricing with biased offline data.
method Identify δ 2 δ^2 δ 2 to measure data bias, use OFU policy and robust variant for unknown bias. result Achieve minimax-optimal regret bounds for contextual pricing.