Cover Image

Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Zeji, Pan, Chaoyi, Shi, Guanya, Qu, Guannan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 90C26, 68T07
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
by: Ustaomeroglu, Muhammed, et al.
Published: (2025)

Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models
by: Lapucci, Matteo, et al.
Published: (2024)

Representation and Regression Problems in Neural Networks: Relaxation, Generalization, and Numerics
by: Liu, Kang, et al.
Published: (2024)

FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation
by: Qiao, Xin, et al.
Published: (2026)

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
by: Lapucci, Matteo, et al.
Published: (2024)

Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization
by: Jeong, Halyun, et al.
Published: (2025)

Tracking the Median of Gradients with a Stochastic Proximal Point Method
by: Schaipp, Fabian, et al.
Published: (2024)

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
by: Lee, Wooin, et al.
Published: (2026)

Model-Based Diffusion for Trajectory Optimization
by: Pan, Chaoyi, et al.
Published: (2024)

Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
by: Lanzillotta, Francesca, et al.
Published: (2026)

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks
by: Chen, Po, et al.
Published: (2025)

Iso-Riemannian Optimization on Learned Data Manifolds
by: Diepeveen, Willem, et al.
Published: (2025)

Global Optimization with A Power-Transformed Objective and Gaussian Smoothing
by: Xu, Chen
Published: (2024)

Convergence of gradient descent for deep neural networks
by: Chatterjee, Sourav
Published: (2022)

Global Optimization of Gaussian processes
by: Schweidtmann, Artur M., et al.
Published: (2020)

CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
by: Du, Wenzhang
Published: (2025)

Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits
by: Murray, Michael, et al.
Published: (2025)

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications
by: Lee, Youngkyu, et al.
Published: (2024)

Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
by: Kopaničáková, Alena, et al.
Published: (2023)

Transport, Don't Generate: Deterministic Geometric Flows for Combinatorial Optimization
by: Friedmann, Benjy, et al.
Published: (2026)

Global Convergence of Adjoint-Optimized Neural PDEs
by: Riedl, Konstantin, et al.
Published: (2025)

Exponential convergence rates for momentum stochastic gradient descent in the overparametrized setting
by: Gess, Benjamin, et al.
Published: (2023)

CRAFT: Conflict-Resolved Aggregation for Federated Training
by: Wang, Ziqi, et al.
Published: (2026)

Generalizing Adam to Manifolds for Efficiently Training Transformers
by: Brantner, Benedikt
Published: (2023)

BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
by: Zhang, Hengrui, et al.
Published: (2026)

Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
by: Troxell, David, et al.
Published: (2026)

PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming
by: Tang, Bo, et al.
Published: (2022)

An Augmented Lagrangian Method for Training Recurrent Neural Networks
by: Wang, Yue, et al.
Published: (2024)

Moments, Time-Inversion and Source Identification for the Heat Equation
by: Liu, Kang, et al.
Published: (2025)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
by: Brännvall, Rickard, et al.
Published: (2023)

Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy
by: Sao, Piyush
Published: (2026)

Uncomputability of Global Optima for Nonconvex Functions in the Oracle Model
by: Lakshmanan, K
Published: (2023)

Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis
by: Hennadii, Kutomanov
Published: (2026)

Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models
by: Jin, Cheng, et al.
Published: (2025)

Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
by: Cantürk, Semih, et al.
Published: (2026)

Quantum-Inspired DRL Approach with LSTM and OU Noise for Cut Order Planning Optimization
by: Chrisnanto, Yulison Herry, et al.
Published: (2025)

A Two-Phase Adaptive Balanced Penalty Method for Controllable Pareto Front Learning under Split Feasibility Conditions
by: Hoang, Nguyen Viet, et al.
Published: (2026)

Revisiting Frank-Wolfe for Structured Nonconvex Optimization
by: Maskan, Hoomaan, et al.
Published: (2025)

A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization
by: Qiu, Junwen, et al.
Published: (2023)

Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients
by: Wu, Rui, et al.
Published: (2026)