This paper improves the foundations of neural likelihood approximation for Bayesian inverse problems by making the learning problem strictly convex and showing convergence to the true likelihood.

This paper analyzes the statistical and computational limits of learning bounded linear operators between Sobolev spaces from noisy data, and constructs a finite-resolution blockwise least-squares est…

This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.

This paper proposes a hierarchical Bayesian model and an efficient MCMC algorithm to tackle ill-posed inverse problems in the presence of non-linear forward models, additive and multiplicative noise,…

This paper establishes a direct connection between Approximate Message Passing (AMP) and the Convex Gaussian Min-max Theorem (CGMT) for regularized linear regression and M-estimation.

This paper systematically explores the convex polygon reconstruction problem with specified sets of features, contributing new testing algorithms and hardness results.

The paper introduces MINTS, a minimalist Bayesian framework that simplifies sequential decision-making by placing priors only on the optimum location, allowing for the incorporation of structural cons…

The paper analyzes a new class of asynchronous adaptive first-order optimization methods and proves their stochastic convergence rate is O(1/sqrt{t}) for non-convex functions.

This paper develops statistical learning theory for gradient boosting in Peaks-over-Threshold modeling using Generalized Pareto distributions, deriving error bounds and reducing gradient correlation.

This paper proves conditions for efficiently approximating expectations of certain functions with respect to standard Gaussian or symmetric exponential probability measures.

This paper proves convergence of belief propagation algorithms for multipath data association to a unique fixed point.

This paper constructs strictly convex quadratic problems and initial points for which the long Barzilai--Borwein method does not converge root-superlinearly.

The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state…

This paper investigates the necessity of interaction for order-optimal 1-bit mean estimation in nonparametric finite-moment classes.