#convergence analysis

try —

27 papers match

cs.LG2026

The Convergence Behavior of Adam under Heavy-Tailed Noise

Yijiang Pang

The paper provides the first convergence guarantees for the standard vector-form Adam optimizer under heavy‑tailed stochastic noise, showing convergence to stationary points with s…

#optimization#stochastic optimization#adam optimizer#heavy-tailed noise
math.OC2026

A new theorem of alternatives leading to sufficient conditions for the superiorization guarantee question of Dynamic String-Averaging in the inconsistent case

Kay Barshad, Yair Censor

The paper introduces a new theorem of alternatives for the Superiorization Methodology applied to General Dynamic String-Averaging in inconsistent feasibility problems, providing s…

#superiorization#string-averaging#convex feasibility#inconsistent case
math.OC2026

Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction

Hiroki Hamaguchi, Yuya Hikima, Hiroshi Sawada +1

The paper proposes a gradient-based optimization algorithm that estimates distribution shifts via finite differences, providing convergence guarantees for a wider range of loss fun…

#performative prediction#gradient-based optimization#distribution shift#convergence analysis
math.NA2026

Convergence of entropy-conservative summation-by-parts discretizations to smooth solutions of hyperbolic conservation laws

Hendrik Ranocha

The paper extends convergence analysis for entropy-conservative summation-by-parts (SBP) discretizations to general hyperbolic systems with convex entropy and source terms, and to…

#entropy-conservative methods#summation-by-parts#hyperbolic conservation laws#convergence analysis
math.OC2026

Optimization under Persistent State-Dependent Bias: Gradient-based Method and Complexity Analysis

Zhaoxian Wu, Quan Xiao, Tayfun Gokmen +1

The paper analyzes how stochastic gradient descent behaves when updates are consistently distorted by state-dependent scaling, shows this leads to a biased solution, and introduces…

#stochastic gradient descent#state-dependent bias#bilevel optimization#convergence analysis
math.OC2026

Proximal Gradient Methods for Unconstrained Set Optimization Problems with Set-Valued Maps of Finite Cardinality

Ravi Raushan, Debdas Ghosh, Anshika +1

The paper proposes two proximal gradient algorithms (with and without an Armijo‑type line search) for unconstrained set‑valued optimization problems with finitely many component fu…

#set-valued optimization#proximal gradient methods#line search#convergence analysis
math.OC2026

Inertial Primal Dual Dynamics with Hessian-driven Damping for Saddle Point Problems

Zepeng Wang, Juan Peypouquet

The paper introduces two inertial primal‑dual dynamical systems with Hessian‑driven damping to solve smooth saddle‑point problems, proving fast convergence rates for both convex‑co…

#primal-dual dynamics#saddle point problems#inertial methods#Hessian damping
math.NA2026

A low-rank hierarchical framework for the non-Markovian stochastic Schrödinger equation with convergence analysis

Zhuohan Zhang, Zhenning Cai

The paper introduces a low‑rank hierarchical numerical method for solving the non‑Markovian stochastic Schrödinger equation, provides a rigorous convergence analysis, and shows tha…

#low-rank approximation#non-markovian dynamics#stochastic schrödinger equation#hierarchical equations
math.NA2026

Fully discrete least-squares splitting scheme for the Monge-Ampère equation: finite element analysis and convergence

Anna Peruso

The paper introduces a fully discrete finite element framework for the two‑dimensional Dirichlet Monge‑Ampère equation using a least‑squares splitting algorithm, and provides conve…

#monge-ampere equation#finite element methods#least-squares splitting#convergence analysis
math.OC2026

Full Convergence of Regularized Methods for Unconstrained Optimization

Andrea Cristofari

The paper shows that unconstrained optimization algorithms using locally quadratic models regularized by a high‑order norm term generate a fully convergent sequence of iterates for…

#unconstrained optimization#regularized methods#convergence analysis#pseudoconvex functions
cs.LG2026

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

Zeyang Li, Chuxiong Hu, Yunan Wang +4

The paper shows that regularized policy iteration in reinforcement learning is mathematically equivalent to applying the Newton‑Raphson method to a smoothed Bellman equation, provi…

#regularized policy iteration#newton-raphson method#convergence analysis#entropy regularization
cs.LG2026

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity

Kumar Kshitij Patel, Rustem Islamov, Sebastian U Stich +3

The paper establishes tighter convergence rates for Local SGD (Federated Averaging) on general convex problems under a bounded second‑order heterogeneity assumption, and provides n…

#local sgd#federated learning#convex optimization#heterogeneous data
math.NA2026

Convergence of the Markovian Iteration for Coupled FBSDEs via a Differentiation Approach

Zhipeng Huang, Cornelis W. Oosterlee

The paper presents a new differentiation-based technique to ensure convergence of a Markovian iteration method for solving fully coupled forward-backward stochastic differential eq…

#forward-backward stochastic differential equations#markovian iteration#numerical methods#coupled drift
stat.ML2026

Convergence Rates for Distribution Matching with Sliced Optimal Transport

Gauthier Thurin, Claire Boyer, Kimia Nadjahi

The paper analyzes an iterative sliced optimal transport method for matching probability distributions, providing non‑asymptotic convergence rates and showing how the method behave…

#optimal transport#sliced wasserstein#distribution matching#convergence analysis
math.NA2026

Approximation of solutions of parameter-dependent problems by residual neural networks

Ana Carpio

The paper introduces a simple training scheme for residual neural networks based on analytic activation functions and gradient flows, with convergence guaranteed by Lojasiewicz the…

#residual neural networks#parametric problems#gradient flow training#inverse problems
math.FA2026

A residual-iteration framework for alternating projections between affine subspaces

Nguyen T. Thao

The paper reformulates alternating projections between two affine subspaces as a least‑squares problem, introduces a residual‑state iteration framework that includes Landweber, ste…

#alternating projections#affine subspaces#least-squares optimization#residual iteration
math.NA2026

NGMRES convergence analysis and proof of acceleration for contractive and noncontractive iterations

Y. He, L. Rebholz, M. Xiao

The paper provides the first theoretical convergence analysis of nonlinear GMRES (NGMRES) for both contractive and noncontractive fixed‑point iterations, identifying the ratio‑gain…

#nonlinear gmres#fixed point iteration#convergence analysis#acceleration methods
math.NA2026

Multiscale Methods for Discretized Continuous Optimization: Convergence and Cost Analysis

Nicholas J. E. Richardson, Noah Marusenko, Michael P. Friedlander

The paper studies a multiscale algorithm that solves a sequence of increasingly fine discretizations of continuous optimization problems, using coarse solutions to warm‑start finer…

#multiscale methods#discretized optimization#convergence analysis#cost analysis
math.OC2026

Quantitative asymptotic regularity and -asymptotic regularity for the inexact generalized Halpern iteration

Nicoleta Dumitru, Laurentiu Leustean

The paper uses proof‑mining techniques to derive explicit quantitative bounds on the asymptotic and T‑asymptotic regularity of an inexact generalized Halpern iteration, a viscosity…

#proof mining#asymptotic regularity#halpern iteration#fixed point algorithms
math.DS2026

Global Convergence of the Return Dynamics in the Class

Mohammed Barkatou, Mohamed El Morsalani

The paper studies a return map defined on domains with a fixed convex core, showing that its dynamics act like an adaptive gradient descent on the domain’s thickness function and c…

#geometric dynamics#convex geometry#return map#gradient descent analogy
math.OC2026

Adaptive Metrics for Norm-Minimization-Based Outer Approximation in Convex Vector Optimization

Mohammed Alshahrani

The paper proposes an adaptive-metric framework for norm‑minimization outer‑approximation algorithms in bounded convex vector optimization, proving convergence rates for any inner‑…

#convex vector optimization#outer approximation#adaptive metrics#norm minimization
math.OC2026

Semismooth Newton methods for degenerate polyhedral projection

Chao Ding, Fuxiaoyue Feng, Xudong Li

The paper develops dual semismooth Newton algorithms for degenerate polyhedral projection problems by exploiting a primal‑dual lifted representation that ensures nonsingular genera…

#semismooth newton#polyhedral projection#degenerate optimization#dual methods
math.NA2026

Hermite spectral approximation for functions with endpoint singularities using exponential transforms

Haiyong Wang

The paper proposes Hermite spectral approximations for functions with endpoint singularities using single, double, and error‑function exponential transforms, provides convergence a…

#hermite spectral methods#exponential transforms#endpoint singularities#convergence analysis
math.OC2026

Nonasymptotic Analysis of Accelerated Methods With Inexact Oracle Under Absolute Error Bound

Yin Liu, Sam Davanloo Tajbakhsh

The paper derives explicit nonasymptotic convergence bounds for two accelerated first‑order methods applied to smooth convex problems when gradients are accessed with bounded absol…

#accelerated methods#inexact gradient#convex optimization#performance estimation problem
← Prev1 / 2Next →

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.