Study noise-free kernel bandits, finding upper bounds on regret.
problem Optimizing unknown functions without noise.
method Upper bounds on regret for noise-free kernel-based bandits.
result No order optimal regret bounds are established, conjecture on optimal bound.
New RL method handles large state-action spaces with complex models.
problem Complex models and large state-action spaces in reinforcement learning.
method π-KRVI, an optimistic modification of least-squares value iteration using kernel ridge regression.
result First order-optimal regret guarantees under general settings, improving over state of the art.
Bayesian optimization algorithm reduces regret with efficient region pruning.
problem Sequential optimization of unknown functions in high-dimensional spaces.
method Gaussian process-based, domain shrinking through tree-based region pruning.
result Order-optimal regret performance with reduced computational complexity.
Random exploration optimizes Bayesian optimization with optimal error rates and computational efficiency.
problem Optimizing Gaussian Process models in Bayesian optimization.
method Random sampling from a distribution in an infinite dimensional Hilbert space, with domain shrinking and order-optimal regret guarantees.
result Achieves optimal error rates and computational efficiency in both noise-free and noisy settings.
A new metric, Weighted Regret, unifies FDR and power evaluation in online multiple testing.
problem The asymmetric costs of false positives and false negatives in automated pipelines.
method Introducing Weighted Regret and Decoupled-OMT (DOMT) to unify FDR and power evaluation.
result DOMT achieves an order-optimal sublinear mitigation of threshold depletion in bursty environments.
The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially unknown to the secondary users and are estimated using sensing decisions. There is no explicit information exchange or prior agreement amon…
We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actions. In this setting, the feedback information system can be represented by a graph, and previous works studied the expected regret of the le…
DAL enhances black-box bandit algorithms for non-stationary environments.
problem Non-stationary environments in bandit problems.
method DAL combines any stationary bandit algorithm with a change detector.
result DAL consistently outperforms state-of-the-art methods in various non-stationary scenarios.
New methods combat data poisoning attacks in bandit algorithms using limited verification.
problem Data poisoning attacks on bandit algorithms, especially in the UCB and ETC types.
method Verification-based mechanisms to restore optimal regret with limited verifications.
result A simple modified ETC type bandit algorithm can restore optimal regret with O ( log T ) O(\log T) O ( log T ) verifications. LAZO reduces query complexity and variance in ZO methods.
problem High query complexity and variance in zeroth-order optimization.
method LAZO uses adaptive lazy queries to reduce variance and save queries.
result LAZO achieves lower regret and query complexity compared to existing methods.
This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget B B B that can be spent to perform actions, an…
Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabilities on the reward distributions: the classic K K K -armed bandit and the linearly parameterized bandit…
Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.
problem Minimizing regret in collaborative multi-agent bandit problems.
method Proposed an algorithm with optimal regret bounds for collaborative multi-agent multi-armed bandit model.
result First algorithm with order optimal regret bounds for collaborative bandit model.
Unified theory for UCB policies in total and max bandit problems.
problem Order optimality of UCB policies in max bandit problems.
method Unified definition of UCB policy using oracle quantity and failure count.
result UCB policies are order optimal in both total and max bandit problems.
Paper tackles performative prediction without convexity assumptions.
problem Performative prediction where data distribution changes with model deployment.
method Reparameterization framework to transform non-convex objective into convex one.
result Provably sublinear regret guarantees for learnable model.
Optimal simple regret bound for Gaussian Process bandits.
problem Sequential optimization of expensive-to-evaluate functions.
method Proved a bound on simple regret for pure exploration algorithms.
result Order optimal bound on simple regret for Gaussian Process bandits.
Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterizes the effect of forgetting factors for a class of online Newton algorithms. For exp-concave and strongly convex objectives, the algorithms a…
Algorithm reduces regret in distributed kernel bandits with shared randomness.
problem Minimizing regret in collaborative function maximization.
method Uniform exploration at local agents and shared randomness with central server.
result Achieves optimal regret order with sublinear communication cost.
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. We consider combinatorial online learning with subset choices when only relative feedback information from subsets is available, instead of bandit or semi-bandit feedback which is absolute. Specifically, we study two regret minimisation problems over subsets of a finite ground set [ n ] [n] [ n ] , with subset-wise relative prefe…
LaPSRL achieves optimal regret for isoperimetric RL distributions.
problem Designing RL algorithms with sublinear regret for non-log-concave distributions.
method Posterior Sampling (PSRL) and Langevin sampling (LaPSRL) for isoperimetric distributions.
result LaPSRL achieves order-optimal regret and subquadratic complexity.
Sketchy reduces memory and compute requirements for adaptive regularization in deep learning.
problem Prohibitive memory and running time for adaptive regularization methods in deep learning.
method Low-rank sketching approach using Frequent Directions (FD) to reduce memory and compute requirements.
result Efficient interpolation between resource requirements and degradation in regret guarantees with rank k k k . Master algorithm fails to detect non-stationarity in practical settings.
problem Non-Stationary Reinforcement Learning without prior knowledge.
method Master algorithm tested under various conditions, including piecewise stationary multi-armed bandits.
result Master's non-stationarity detection is ineffective for practical horizons, leading to performance similar to random restarting.
We consider stochastic multi-armed bandits where the expected reward is a unimodal function over partially ordered arms. This important class of problems has been recently investigated in (Cope 2009, Yu 2011). The set of arms is either discrete, in which case arms correspond to the vertices of a finite graph whose stru…
Actor-Critic method achieves optimal regret for unichain MDPs.
problem Scalable regret analysis for infinite-horizon average-reward MDPs.
method NAC-B, a Natural Actor-Critic with batching.
result Order-optimal regret of i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) in infinite-horizon average-reward MDPs. We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations of classic bandit algorithms to the correlated setting. We present a unified proof technique to anal…
TSAC achieves optimal frequentist regret in adaptive control of LQRs.
problem Adaptive control of stabilizable linear-quadratic regulators with unknown dynamics.
method Thompson Sampling (TS) for adaptive control of LQRs, with a novel early exploration strategy.
result Achieves i l d e O ( T ) ilde O(\sqrt{T}) i l d e O ( T ) regret, optimal for multidimensional systems. The paper develops algorithms to minimize queue length regret in a communication system.
problem Minimizing the difference between actual and optimal queue lengths over time slots.
method Introduces queue length regret and applies algorithms from stochastic multi-armed bandit problem to analyze system performance.
result Order optimal O ( 1 ) O(1) O ( 1 ) queue length regret can be achieved with queue-length based policies. Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.
problem Optimizing personalized objectives in a distributed system with limited global information.
method Kernel-based bandit framework with surrogate Gaussian process models, sparse approximations.
result Order-optimal regret performance (up to polylogarithmic factors) and reduced communication overhead.
FTPL method shows near-optimal regret bounds for AMDPs with bandit feedback.
problem Minimizing regret in AMDPs with adversarial losses and bandit feedback.
method Follow-the-Perturbed-Leader (FTPL) method for AMDPs.
result FTPL achieves near-optimal regret bounds for AMDPs with bandit feedback.
DP-NCB algorithm ensures privacy and fairness in bandit decisions.
problem Achieving both privacy and fairness in bandit algorithms.
method Differentially Private Nash Confidence Bound (DP-NCB) framework.
result DP-NCB achieves optimal Nash regret while maintaining privacy.
New algorithm learns optimal policy with multi-step lookahead information.
problem Learning optimal policy in reinforcement learning with multi-step lookahead information is NP-hard.
method Adaptive batching policies that process lookahead in state-dependent chunks.
result Order-optimal regret bounds up to a constant factor of lookahead horizon.
Algorithm learns diverse rankings for search engines.
problem Designing algorithms for search engines to rank diverse items.
method LDR (Learning Diverse Rankings) algorithm, efficient learning based on users' feedback.
result Algorithm achieves optimal ranking performance with O ( ( N − L ) log ( T ) ) O((N-L)\log(T)) O (( N − L ) log ( T )) regret. 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.
New algorithms improve linear bandit performance with low computation.
problem Optimizing reward in linear stochastic bandits.
method Reward-biased maximum likelihood method modified for linear and generalized linear bandits.
result New policies achieve order-optimality and competitive empirical performance.
A federated learning algorithm tackles linear bandits with adversarial actions, achieving optimal regret bounds.
problem Federated linear bandits with finite adversarial action sets.
method FedSupLinUCB algorithm, extending SupLinUCB and OFUL principles.
result Achieves a total regret of i l d e O ( d T ) ilde{O}(\sqrt{d T}) i l d e O ( d T ) , matching minimax lower bound and being order-optimal. Inspired by the Reward-Biased Maximum Likelihood Estimate method of adaptive control, we propose RBMLE -- a novel family of learning algorithms for stochastic multi-armed bandits (SMABs). For a broad range of SMABs including both the parametric Exponential Family as well as the non-parametric sub-Gaussian/Exponential f…
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.
Optimizes CM for stochastic convex optimization with progressive precision.
problem Stochastic nature of objective function in convex optimization.
method Iterative coordinate minimization with optimal precision control.
result Order-optimal regret performance for strongly convex and nonsmooth functions.
We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the…
Second-order optimizers retain residual information after data deletion, affecting machine unlearning.
problem Residual information in second-order optimizers after data deletion.
method Comparison of first-order and second-order learners, eigendecomposition analysis.
result Second-order optimizers retain residual information, not detectable by first-order analysis.
New protocols show 1-bit mean estimation can be order-optimal without interaction.
problem Can 1-bit mean estimation be optimal without interaction?
method Adaptive and non-adaptive threshold and interval queries, with one adaptive transition.
result Arbitrary non-adaptive quantizers can match the adaptive rate, suggesting interaction is not necessary.
New algorithm reduces age of information in wireless networks with unknown channel reliability.
problem Learning optimal source-channel pairs to minimize age of information in wireless networks.
method Introduces AoI regret, novel learning algorithm with bounded AoI regret.
result Developed a learning algorithm with O ( 1 ) O(1) O ( 1 ) AoI regret, improving upon Θ ( log T ) Θ(\log T) Θ ( log T ) . Data whitening and second order optimization harm generalization by reducing access to dataset information.
problem Harmful effects of data whitening and second order optimization on generalization in machine learning.
method Analysis of fully connected models and experimental verification.
result Data whitening and second order optimization reduce or prevent generalization by limiting access to dataset information.
New algorithm optimizes dueling bandits for both stochastic and adversarial preferences.
problem Optimizing decision-making in environments where only relative preferences are observed.
method Proposed a reduction from dueling bandits to multi-armed bandits, achieving optimal regret bounds.
result First best-of-both-world result for dueling bandits, optimal regret bound for Condorcet-winner benchmark.
New algorithm optimizes Hölder smooth functions in RKHS with tighter regret bounds.
problem Optimizing Hölder smooth functions in RKHS with bounded norm.
method Proposes a new algorithm ( exttt{LP-GP-UCB}) using Local Polynomial (LP) estimators and multi-scale UCB.
result Derives high probability bounds on simple and cumulative regret, matching optimal performance for SE kernel and uniformly tighter bounds for Matérn kernels.
Study optimizes zero-order strongly convex function minimization with higher order smoothness.
problem Optimizing a strongly convex function with noisy evaluations.
method Randomized approximation of projected gradient descent with smoothing kernel.
result Upper bounds and minimax lower bounds for the algorithm, showing near-optimality.
Algorithm identifies the best arm in linear bandits with high probability.
problem Best arm identification in linear multi-armed bandits with noisy measurements.
method Phased Elimination Linear Exploration Game (PELEG) using no-regret learners.
result PELEG achieves sample complexity matching lower bounds.