New robust control method for uncertain systems using bootstrapped noise.
problem Designing controllers robust to model uncertainties in finite data.
method Least-squares model estimator, bootstrap resampling, multiplicative noise LQR.
result Significantly outperforms certainty equivalent controllers in numerical tests.
Novel framework for uncertainty quantification in metric spaces.
problem Uncertainty quantification in regression models with metric responses.
method Developed algorithms for large datasets, agnostic to predictive models, with asymptotic and non-asymptotic guarantees.
result Asymptotic and non-asymptotic guarantees for special cases, demonstrated in clinical applications.
Paper studies robust MDPs, improving sample complexity and asymptotic performance.
problem Optimal robust policy and value function in robust MDPs with generative models.
method Improves prior results on non-asymptotic and asymptotic performances of robust MDPs, considering various uncertainty sets.
result Improved sample complexity and asymptotic normality of optimal robust value function.
Develops a new method for uncertainty quantification in high-dimensional learning.
problem Challenges in uncertainty quantification in high-dimensional regression or learning problems.
method Data-driven approach for UQ that corrects bias terms from training data.
result Non-asymptotic confidence intervals that avoid overestimating uncertainty.
Efficiently constructs prediction bands with minimal assumptions.
problem Uncertainty quantification for nonparametric, heteroscedastic data.
method Semi-definite programming for data-adaptive prediction bands.
result Strong non-asymptotic coverage properties with minimal distributional assumptions.
Develops a framework for inferring causal relationships in networked data with uncertainty quantification.
problem Extracting reliable inference from complex Hawkes network data with uncertainty.
method Statistical inference framework based on maximum likelihood estimation and concentration inequalities of continuous-time martingales.
result Provides a non-asymptotic confidence set for uncertainty quantification.
Bayesian neural networks use ridgelet prior for uncertainty quantification.
problem Combining strong predictive performance with uncertainty quantification in Bayesian neural networks.
method Proposes a ridgelet prior that approximates a Gaussian process covariance function in the output space of the network.
result Establishes universality property allowing Bayesian neural networks to approximate any Gaussian process.
New bounds for kernel regression under non-Gaussian noise.
problem Uncertainty quantification for function estimates from noisy observations.
method Novel non-asymptotic probabilistic uniform error bounds for kernel-based regression.
result Proposed bounds apply to a broad class of non-Gaussian noise distributions.
New method improves uncertainty quantification for large batch sizes and misspecified models.
problem Challenges in tuning algorithms for accurate uncertainty quantification in large batch sizes and misspecified models.
method Proposes new discrete-time approximations to SGD and SGLD, proving error bounds for practical tuning.
result Quantitative, non-asymptotic error bounds for accurate predictions of covariance and autocorrelation time.
New method for time series prediction with uncertainty quantification.
problem Uncertainty quantification for multi-dimensional time series predictions.
method Flow-based conformal prediction for time series.
result Significantly smaller prediction sets with target coverage.
fSGLD optimizes deep learning by favoring flat regions in the loss landscape.
problem Understanding and improving the behavior and generalization of deep learning algorithms.
method Flatness-Aware Stochastic Gradient Langevin Dynamics (fSGLD) that biases learning towards flat basins.
result fSGLD targets a flatness-biased Gibbs distribution with explicit excess risk guarantees.
The paper studies binary classification and aims at estimating the underlying regression function which is the conditional expectation of the class labels given the inputs. The regression function is the key component of the Bayes optimal classifier, moreover, besides providing optimal predictions, it can also assess t…
We study statistical detection of grayscale objects in noisy images. The object of interest is of unknown shape and has an unknown intensity, that can be varying over the object and can be negative. No boundary shape constraints are imposed on the object, only a weak bulk condition for the object's interior is required…
Thompson Sampling with bilateral uncertainty improves performance in Bayesian Optimization.
problem Twin difficulties of modeling and searching complex functions in high dimensions.
method Exploiting conditional independence, Thompson Sampling respecting bilateral uncertainty (BU).
result Thompson Sampling with BU is more effective than the additive approximation in small budgets.
We propose a data-driven approach to quantify the uncertainty of models constructed by kernel methods. Our approach minimizes the needed distributional assumptions, hence, instead of working with, for example, Gaussian processes or exponential families, it only requires knowledge about some mild regularity of the measu…
Paper quantifies uncertainty in pairwise comparison models.
problem Uncertainty quantification in sparse Bradley-Terry-Luce models.
method Unified proof strategy for MLE and spectral estimator.
result Sharp and uniform non-asymptotic expansions for estimators.
Adaptive learning method for stochastic programs with latent uncertainty.
problem Stochastic programming problems with implicitly decision-dependent uncertainty.
method Adaptive learning-based surrogate method integrating simulation and statistical estimates.
result Established non-asymptotic convergence rate analysis for enhanced stability and efficiency.
This review examines bandit problems in AI using statistical methods.
problem Sequential decision-making under uncertainty in AI environments.
method Foundational models, concentration inequalities, minimax regret bounds, frequentist and Bayesian algorithms, K-armed contextual bandits, SCAB, functional data analysis.
result Exploration-exploitation trade-offs and regret analyses in various bandit problems.
Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.
problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.
Paper addresses trade-off between robustness and specificity in machine learning.
problem Combating distributional uncertainties in training data compared to population distributions.
method Unified framework that unifies Bayesian, distributionally robust optimization, and regularization methods.
result Reveals the trade-off between robustness and specificity.
Proposes FedPop for personalised federated learning with uncertainty quantification.
problem Uncertainty quantification and client drift in personalised federated learning.
method FedPop recasts FL into population modeling with Markov chain Monte Carlo methods.
result Non-asymptotic convergence guarantees for uncertainty quantification.
The paper improves confidence ellipsoids for ridge regression with PAC bounds.
problem Uncertainty quantification in ridge regression for insufficiently exciting inputs.
method Extension of SPS EOA algorithm to ridge regression with PAC bounds.
result Explicitly shows how regularization parameter affects region sizes and provides tighter bounds.
Conformal prediction provides distribution-free uncertainty quantification for black-box models.
problem Uncertainty quantification for high-risk machine learning applications.
method Conformal prediction creates valid uncertainty sets without distributional assumptions.
result Sets contain the ground truth with a specified probability, e.g., 90%.
New algorithms improve robust reinforcement learning under uncertainty.
problem Robust reinforcement learning in MDPs with contamination.
method Non-asymptotic convergence analysis of Q-learning and actor-critic methods. result Efficient algorithms learn robust policies with minimal samples.
Noisy matrix completion aims at estimating a low-rank matrix given only partial and corrupted entries. Despite substantial progress in designing efficient estimation algorithms, it remains largely unclear how to assess the uncertainty of the obtained estimates and how to perform statistical inference on the unknown mat…
The paper proves how Transformers learn from context and generalize well.
problem Understanding how Transformers generalize from diverse tasks.
method Developed a statistical theory for in-context learning, separating risk into Bayes Gap and Posterior Variance.
result The Posterior Variance is task-independent, and the Bayes Gap decreases with more in-context examples.
Study shows robust method for estimating density ratios even with heavy contamination.
problem Estimating density ratios in the presence of heavy contamination.
method Weighted density ratio estimation (DRE) with doubly strong robustness.
result Weighted DRE achieves sparse consistency under heavy contamination.
Paper proposes a new dynamic pricing method with always-valid online statistical learning.
problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.
Constructs non-asymptotic confidence regions for unknown functions in RKHS.
problem Global probabilistic confidence regions for unknown functions in RKHS.
method Reduces confidence region construction to estimating RKHS norm.
result Valid confidence regions can be constructed non-asymptotically.
We provide non-asymptotic convergence rates of the Polyak-Ruppert averaged stochastic gradient descent (SGD) to a normal random vector for a class of twice-differentiable test functions. A crucial intermediate step is proving a non-asymptotic martingale central limit theorem (CLT), i.e., establishing the rates of conve…
Constructing an efficient parameterization of a large, noisy data set of points lying close to a smooth manifold in high dimension remains a fundamental problem. One approach consists in recovering a local parameterization using the local tangent plane. Principal component analysis (PCA) is often the tool of choice, as…
New algorithm quantifies uncertainty in regression models for complex data types.
problem Uncertainty quantification in regression models for complex data types.
method Model-free uncertainty quantification algorithm based on conditional depth measures and kernel mean embeddings.
result Provides faster convergence rates and non-asymptotic guarantees for prediction regions.
New methods improve uncertainty quantification in dynamic biological systems.
problem Uncertainty in dynamic biological models due to nonlinearity and parameter sensitivity.
method Conformal inference methods for non-asymptotic guarantees.
result Enhanced robustness and scalability for diverse biological data structures.
The paper studies reward concentration in MDPs, covering asymptotic and non-asymptotic settings.
problem Reward concentration in Markov Decision Processes (MDPs).
method Unified approach to reward concentration in MDPs, including asymptotic and non-asymptotic bounds.
result Rate-equivalent definitions of regret for learning policies.
A tutorial on non-asymptotic system identification methods.
problem Identifying system parameters in linear models.
method Covering technique, Hanson-Wright Inequality, method of self-normalized martingales.
result Streamlined proofs of least-squares based estimator performance.
We prove non-asymptotic lower bounds on the expectation of the maximum of d independent Gaussian variables and the expectation of the maximum of d independent symmetric random walks. Both lower bounds recover the optimal leading constant in the limit. A simple application of the lower bound for random walks is an (…
We derive generalization error bounds for traditional time-series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space models. These non-asymptotic bounds need only weak assumptions on the data-generating…
New insights on active sequential prediction for mean estimation.
problem Active sequential prediction-powered mean estimation problem.
method Combining uncertainty-based suggestion with a constant probability, analyzing non-asymptotic bounds, and using no-regret learning.
result The optimal query probability is close to the constraint when using no-regret learning.
This work develops confidence intervals for off-policy evaluation.
problem Estimating expected reward with uncertainty quantification.
method Primal-dual optimization with kernel Bellman loss and martingale concentration inequality.
result Developed practical algorithm for non-asymptotic confidence intervals.
Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.
problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.
method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.
result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.
This paper investigates WDRO for nonparametric regression, achieving robustness against distributional uncertainty.
problem Addressing model misspecification in nonparametric regression under distributional uncertainty.
method Wasserstein distributionally robust optimization (WDRO) with structural distinction based on Wasserstein distance order.
result Achieves a convergence rate of n−2β/(d+2β) up to logarithmic factors, showing minimax optimality. The paper analyzes methods for estimating linear functionals from observational data, proving upper bounds and showing optimal procedures.
problem Estimating linear functionals from observational data in causal inference and bandit literature.
method Two-stage procedures that first estimate treatment effect function, then use it to estimate the linear functional.
result Proves non-asymptotic upper bounds on mean-squared error for two-stage procedures and shows instance-dependent optimality.
VRPG algorithm optimizes convex constraints with non-asymptotic guarantees.
problem Stochastic convex optimization under convex constraints.
method Natural variance reduced proximal gradient (VRPG) algorithm.
result VRPG achieves local minimax lower bound up to constants and log factor of N. Optimizes prediction error method for time-varying models.
problem Achieving optimal prediction error rates for time-varying models.
method Nonlinear least squares method for time-varying parametric models.
result First rate-optimal non-asymptotic analysis for time-varying models.
This work analyzes DP-SGD for online LDP problems with practical convergence rates.
problem Analyzing DP-SGD for online LDP problems with practical convergence rates.
method Developed a general framework for online LDP model in stochastic optimization problems, conducted non-asymptotic convergence analysis.
result Comprehensive non-asymptotic convergence analysis of the proposed estimators in finite-sample situations.
Paper approximates risk measures using SGD with Langevin dynamics.
problem Approximating arbitrary law invariant risk measures.
method Stochastic Gradient Langevin Dynamics (SGD-Langevin) for general risk measures.
result Non-asymptotic convergence rates of the approximation algorithm.
We develop a probabilistic framework for sequential random projection.
problem Challenges of sequential decision-making under uncertainty.
method Novel construction of a stopped process and method of mixtures.
result Achieved a non-asymptotic probability bound for random projection.
Develops abstention procedure for nonparametric regression via variance testing.
problem Prediction with selective abstention in error-critical machine learning.
method Nonparametric heteroskedastic regression via testing hypothesis on conditional variance.
result Non-asymptotic risk bounds and convergence regimes for the estimator.