This paper establishes a large deviation principle for the generalization error of interpolating classifiers in the overparametrized regime.

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.

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 proposes a randomized iterative method called Sequential Preconditioned Conjugate Gradient Method (SPCG) for large-scale linear statistical models, which significantly reduces computational…

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 introduces Curvature-Weighted Gradient Diversity (CWGD), a geometry-aware measure for optimization noise that reduces the asymptotic optimization error floor by up to a factor of two compar…

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

This paper proposes a data collection strategy using solver iterates to augment datasets for training generative models, improving the efficiency of the data-model-optimization loop in one-sided box-c…

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.

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

A new method for selecting knots in Generalized Additive Models using an extension of adaptive splines and a customized Fellner-Schall scheme.

The paper introduces an operator calculus for population-based optimization methods, establishing a modular Lyapunov principle for their convergence analysis.

The paper introduces a unified theoretical framework for gradient aggregation in multi-objective optimization, establishing convergence rates and sufficient conditions for achieving Pareto stationarit…

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 derives the gradient of the Wolkowicz-Styan upper bound on the maximum eigenvalue of the cross-entropy loss Hessian in three-layer NNs to characterize directions leading to flat minima and…

The paper introduces Gradient-based Behavior Vector-Parameter Delta (GBV-PD), an approach for evolution-aware regression test prioritization in ML-enabled systems using gradient-based behavior vectors…