Thompson Sampling bounds for contextual bandits with sub-Gaussian rewards.
problem Improving the performance of Thompson Sampling in contextual bandits with sub-Gaussian rewards.
method Proved comprehensive bounds on Thompson Sampling expected cumulative regret based on mutual information and lifted information ratio for sub-Gaussian rewards.
result Explicit regret bounds for various contextual bandit scenarios.
Paper improves SLCB regret bound for bounded noise.
problem Stochastic linear contextual bandits with bounded noise.
method Set-membership estimation (SME) and optimism in the face of uncertainty (OFU).
result Improved regret bound of O ( log T ) O(\log T) O ( log T ) . 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 . 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…
The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.
problem Allocating resources on arms with unknown and random rewards.
method Developed two algorithms with optimal regret bounds for b ∈ [ 0 , 1 ] b \in [0,1] b ∈ [ 0 , 1 ] , demonstrating a phase transition at b = 1 / 2 b=1/2 b = 1/2 . result Achieved optimal gap-dependent and gap-independent regret bounds for b ∈ [ 0 , 1 ] b \in [0,1] b ∈ [ 0 , 1 ] . The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+ε, for some ε ∈ ( 0 , 1 ] ε\in (0,1] ε ∈ ( 0 , 1 ] . Surprisingly, moments of order 2 (i.e., finite variance) are suffi…
This paper extends the MAB problem to consider risk-reward tradeoffs.
problem Maximizing reward while accounting for risk in multi-armed bandit problems.
method Introduced the Risk Aware Lower Confidence Bound (RALCB) algorithm to solve the mean-variance MAB problem.
result The RALCB algorithm performs better than the algorithm in Sani et al. (2012) in both independent and dependent scenarios.
The paper analyzes the reward improvement of aligned policies in large language models.
problem Optimizing policies in large language models while staying close to a reference policy.
method Information-theoretic analysis and reduction to exponential order statistics.
result Information-theoretic upper bounds on reward improvement are derived.
New algorithm reduces worst-case regret for heavy-tailed bandits.
problem Stochastic Multi-Armed Bandit problem with heavy-tailed rewards.
method Modified minimax policy MOSS with saturated empirical mean.
result Worst-case regret matching lower bound for heavy-tailed distributions.
A novel algorithm minimizes regret in a multi-agent bandit problem with time-varying random graphs and heterogeneous rewards.
problem Minimizing regret in a multi-agent multi-armed bandit problem with time-varying random graphs and heterogeneous rewards.
method Introduces a novel algorithmic framework combining averaging-based consensus with a weighting technique and upper confidence bound.
result Derives optimal instance-dependent regret upper bounds of order log T \log{T} log T in both sub-gaussian and sub-exponential environments. New algorithm reduces semi-bandit regret using covariance estimates.
problem Complexity of semi-bandits due to joint distribution of outcomes.
method Develops a new sub-exponential distribution family and an algorithm using covariance estimates.
result Proves a new lower bound on expected regret and constructs an algorithm with asymptotic analysis.
The paper tackles best arm identification in contaminated bandits with optimal error guarantees and sample complexity.
problem Best arm identification in stochastic bandits with adversarial reward contamination.
method Proposes two algorithms: a gap-based algorithm and a successive elimination-based algorithm for sub-Gaussian bandits.
result Asymptotically optimal sample complexity for both algorithms.
Algorithm for low-rank matrix bandits with heavy-tailed rewards, achieving nearly optimal regret bound.
problem Stochastic low-rank matrix bandit with heavy-tailed rewards.
method LOTUS algorithm using truncation and dynamic exploration.
result Regret bound of order $ ilde O(d^ rac{3}{2}r^ rac{1}{2}T^ rac{1}{1+δ}/ ilde{D}_{rr})$ without knowing T T T . KL-MS improves regret bounds for multi-armed bandits with bounded rewards.
problem Designing efficient exploration algorithms for multi-armed bandits with bounded rewards.
method Kullback-Leibler Maillard Sampling (KL-MS) for multi-armed bandits with bounded rewards.
result KL-MS achieves a worst-case regret bound of O ( μ ∗ ( 1 − μ ∗ ) K T ln K + K ln T ) O(\sqrt{μ^*(1-μ^*) K T \ln K} + K \ln T) O ( μ ∗ ( 1 − μ ∗ ) K T ln K + K ln T ) . New algorithms detect changes in non-stationary MABs for better performance.
problem Non-stationary MAB environments where arm reward distributions change over time.
method Modular Detection Augmented Bandit (DAB) procedures with improved performance lower bounds.
result Modular DAB procedures achieve order-optimal regret bounds for various change detectors and bandit algorithms.
Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with ε \varepsilon ε -contaminated rewards. We allow an adversary to give arbitrary unbounded contaminated rewards with full knowledge of the past and future. We impose the constraint that for each time t t t the…
New framework controls generalization for heavy-tailed data in RLHF and SGLD.
problem Heavy-tailed data in modern learning pipelines.
method Tail-dependent information-theoretic framework for sub-Weibull data.
result Sharp generalization bounds for heavy-tailed data.
New method tightens sub-Gaussian concentration inequalities.
problem Estimating variance-type parameters of sub-Gaussian distributions.
method Using sub-Gaussian intrinsic moment norm to maximize normalized moments.
result Provides tighter sub-Gaussian concentration inequalities.
New algorithms for efficient learning with long-term rewards in contextual bandits.
problem Efficient learning with long-term rewards in contextual bandits.
method Proposes new algorithms leveraging sparsity to discover dependence patterns and arm parameters.
result Regret upper bounds for data-poor and data-rich regimes, showing improved sample complexity.
Optimizes sub-Gaussian matrices for preserving data distances.
problem Improving the performance of sub-Gaussian matrices in preserving data distances.
method Analyzes sub-Gaussian matrices and their dependence on the sub-Gaussian norm, presenting optimal bounds.
result Optimal dependence on the sub-Gaussian norm for sub-Gaussian matrices as near isometries on sets.
We tackle the problem of estimating a location parameter with differential privacy guarantees and sub-Gaussian deviations. Recent work in statistics has focused on the study of estimators that achieve sub-Gaussian type deviations even for heavy tailed data. We revisit some of these estimators through the lens of differ…
Heavy-tailed distributions are widely used in robust mixture modelling due to possessing thick tails. As a computationally tractable subclass of the stable distributions, sub-Gaussian α α α -stable distribution received much interest in the literature. Here, we introduce a type of expectation maximization algorithm that e…
Sharp sub-Gaussian bounds for subsolutions of Trudinger's equation on Riemannian manifolds.
problem Bounding weak subsolutions of Trudinger's equation on Riemannian manifolds.
method Proving sub-Gaussian upper bounds for weak subsolutions.
result The upper bounds are sharp for specific classes of manifolds, including \(\mathbb{R}^{n}\).
UCB algorithm adapted for large-scale, non-sub-Gaussian problems.
problem Selecting the best alternative from a large set of options with non-sub-Gaussian performance distributions.
method Adapted UCB algorithm for non-sub-Gaussian settings, focusing on sample size and meta-UCB selection.
result UCB algorithms can achieve sample optimality in large-scale, non-sub-Gaussian problems.
Proves new concentration inequalities for sub-gaussian and sub-exponential variables.
problem Understanding functions of independent random variables better.
method Sub-gaussian and sub-exponential conditions, Rademacher complexities, Lipschitz function classes.
result Extension of Rademacher complexities to unbounded sub-exponential distributions.
We investigate the optimality of perturbation based algorithms in the stochastic and adversarial multi-armed bandit problems. For the stochastic case, we provide a unified regret analysis for both sub-Weibull and bounded perturbations when rewards are sub-Gaussian. Our bounds are instance optimal for sub-Weibull pertur…
Study improves self-normalized bounds for vector-valued processes beyond sub-Gaussianity.
problem Limited understanding of self-normalized concentration for vector-valued processes outside sub-Gaussian frameworks.
method Developed concentration inequalities for self-normalized processes with light tails (e.g., Bennett, Bernstein bounds) for vector-valued data.
result Provided new insights and bounds for self-normalized processes with non-sub-Gaussian distributions.
New algorithm converts data into sub-gaussian designs efficiently.
problem Efficiently converting large datasets into sub-gaussian random designs for robust performance.
method Algorithmic Gaussianization through sketching and averaging, using LESS embeddings.
result Efficient data sketches nearly indistinguishable from sub-gaussian designs.
We consider black box optimization of an unknown function in the nonparametric Gaussian process setting when the noise in the observed function values can be heavy tailed. This is in contrast to existing literature that typically assumes sub-Gaussian noise distributions for queries. Under the assumption that the unknow…
Quantum algorithm estimates mean with sub-Gaussian error.
problem Estimating mean of quantum-computed random variables.
method Quantum mean estimation algorithm with sub-Gaussian error rate.
result Achieves nearly-optimal quadratic speedup over classical methods.
Sharp comparison for sub-Gaussian random variables in convex order.
problem Comparing sub-Gaussian random variables in convex order.
method Proving dominance using moment generating functions and convex functions.
result Sharp comparison established between specific sub-Gaussian random variables.
New method reduces summary points for datasets while maintaining quality.
problem Thinning datasets to reduce summary points while maintaining quality.
method Low-rank analysis of sub-Gaussian thinning.
result Guarantees high-quality compression for any distribution and kernel.
Estimates sub-Gaussian parameter with consistent and optimal rates.
problem Estimating sub-Gaussian parameter from random variables.
method Constrained maximization of empirical weighted cumulant generating function.
result Root-n rate estimator is consistent and optimal under certain conditions.
Proposes a new model for clustering with heavier tails.
problem Clustering with heavy-tailed data.
method Finite mixture of skewed sub-Gaussian stable distributions, maximum likelihood estimation, EM algorithm.
result The proposed model can robustly handle heavy-tailed data.
New study shows mean estimation algorithms can't beat sub-Gaussian rate in general.
problem Improving mean estimation beyond worst-case scenarios.
method Constructing counterexamples and introducing neighborhood optimality.
result No reasonable estimator can achieve better than sub-Gaussian error rate for any distribution.
New winsorized mean improves robustness to up to 50% contamination.
problem Improving robustness of mean estimation in the presence of outliers.
method Outlyingness-induced winsorized mean approach.
result Achieves up to 50% contamination robustness with sub-Gaussian performance.
The paper proves a regret bound for a sub-Gaussian mixture on unbounded data.
problem Tackles the challenge of achieving regret bounds for sub-Gaussian mixtures on unbounded data.
method Uses path-wise (deterministic) regret bounds and a cumulative variance process to derive the bound.
result Shows that on a specific event, the regret is eventually bounded by ln(ln V_T).
We study the problem of estimating the mean of a random vector X X X given a sample of N N N independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of X X X exists. The estimator is based on a novel concept of a…
Two new algorithms improve robust PCA and Schatten packing.
problem Robustly estimating the top eigenvector of corrupted sub-Gaussian data.
method Two iterative filtering and nearly-linear time algorithms.
result First polynomial-time algorithms for non-trivial covariance estimation.
Paper analyzes SGMs for learning sub-Gaussian distributions without dimensionality constraints.
problem Learning sub-Gaussian distributions in high dimensions with SGMs.
method Introduced complexity notion and proved approximation and generalization rates.
result SGMs can approximate target sub-Gaussian distributions in total variation with dimension-independent rate.
SVGD algorithm converges at rate 1/sqrt(log log n) for sub-Gaussian distributions.
problem Approximating a probability distribution with particles.
method Stein variational gradient descent (SVGD) with finite particles and sub-Gaussian target distribution.
result SVGD achieves a convergence rate of 1/sqrt(log log n) for sub-Gaussian distributions.
Novel confidence sets improve linear bandit performance by adapting to unknown noise levels.
problem Adapting to unknown noise levels in sequential decision-making.
method Proposed semi-adaptive and variance-adaptive confidence sets.
result Improved regret bounds and better performance in Bayesian optimization tasks.
Improved Thompson Sampling using fractional posteriors achieves better regret bounds.
problem Optimizing regret in stochastic multi-armed bandit problems.
method Using α \alpha α -posterior distributions, derived frequentist regret bounds. result Instance-dependent and instance-independent regret bounds established.
Improved median of means estimator with tighter bounds.
problem Improving the efficiency and reliability of median of means estimator.
method Modification of the median of means estimator with sub-Gaussian deviation bounds.
result Achieves nearly optimal constants under minimal assumptions.
Flexible model captures varying scales in data clusters.
problem Real-world data often exhibits varying scales or intensities, violating the homogeneity assumption of classical Gaussian mixture models.
method Individual-heterogeneous sub-Gaussian mixture model with an efficient spectral method for exact recovery.
result The method provably achieves exact recovery of true cluster labels under mild separation conditions.
Study shows how over-parameterized classifiers can still perform well on noisy data.
problem Understanding how maximum margin classifiers perform in over-parameterized settings with noisy data.
method Analyzes maximum margin classifiers on sub-Gaussian mixtures, providing risk bounds.
result Characterizes conditions for 'benign overfitting' in linear classification problems.
One-bit clustering method for two-component sub-Gaussian mixture models
problem Clustering in sub-Gaussian mixture models
method One-bit clustering using dithered quantization
result Decaying misclassification rate with exponential signal-to-noise ratio
New algorithm reduces unfairness in bandit problems by balancing exploration and exploitation.
problem Fairness in bandit problems where early participants can be unfairly disadvantaged.
method Introduces extsf{UCB-HARE} algorithm that balances exploration and exploitation using inverse-weighted harmonic rank schedule.
result Algorithm extsf{UCB-HARE} achieves regret matching the lower bound Ω ( σ k max ( 1 , q ) / T ) Ω(σ\sqrt{k^{\max(1,q)}/T}) Ω ( σ k m a x ( 1 , q ) / T ) for q > 1 q>1 q > 1 .