Imagen de Portada

Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yi, Mingyang, Wang, Bohan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Closing the gap between SVRG and TD-SVRG with Gradient Splitting
por: Mustafin, Arsenii, et al.
Publicado: (2022)

Learning Theory of the SVRG: Generalization and Convergence Analysis
por: Lei, Yunwen, et al.
Publicado: (2026)

A Coefficient Makes SVRG Effective
por: Yin, Yida, et al.
Publicado: (2023)

SVRG and Beyond via Posterior Correction
por: Daheim, Nico, et al.
Publicado: (2025)

Convergence Analysis of alpha-SVRG under Strong Convexity
por: Xiao, Sean, et al.
Publicado: (2025)

Gradient Flows and Riemannian Structure in the Gromov-Wasserstein Geometry
por: Zhang, Zhengxin, et al.
Publicado: (2024)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
por: Tanguy, Eloi
Publicado: (2023)

Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning
por: Sun, Mingyang, et al.
Publicado: (2025)

Riemannian Denoising Diffusion Probabilistic Models
por: Liu, Zichen, et al.
Publicado: (2025)

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference
por: Nguyen, Dai Hai, et al.
Publicado: (2023)

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
por: Bonet, Clément, et al.
Publicado: (2025)

PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization
por: Ao, Ruicheng, et al.
Publicado: (2026)

Riemannian MeanFlow
por: Woo, Dongyeop, et al.
Publicado: (2026)

Laplace Learning in Wasserstein Space
por: Oliver, Mary Chriselda Antony, et al.
Publicado: (2025)

From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
por: Evron, Itay, et al.
Publicado: (2025)

Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization
por: Gal, Eshed, et al.
Publicado: (2026)

Wasserstein Regression as a Variational Approximation of Probabilistic Trajectories through the Bernstein Basis
por: Maslov, Maksim, et al.
Publicado: (2025)

Demystifying SGD with Doubly Stochastic Gradients
por: Kim, Kyurae, et al.
Publicado: (2024)

Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries
por: Wu, Bohan, et al.
Publicado: (2025)

Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds
por: Bonet, Clément, et al.
Publicado: (2024)

Conditional Lagrangian Wasserstein Flow for Time Series Imputation
por: Qian, Weizhu, et al.
Publicado: (2024)

Stability and Generalization for Decentralized Markov SGD
por: Wang, Jiahuan, et al.
Publicado: (2026)

Canonical Variates in Wasserstein Metric Space
por: Li, Jia, et al.
Publicado: (2024)

Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem
por: Carrasco, Xavier Aramayo, et al.
Publicado: (2023)

Ordered Momentum for Asynchronous SGD
por: Shi, Chang-Wei, et al.
Publicado: (2024)

Data Deletion for Linear Regression with Noisy SGD
por: Xia, Zhangjie, et al.
Publicado: (2024)

Riemannian MeanFlow for One-Step Generation on Manifolds
por: Zhong, Zichen, et al.
Publicado: (2026)

Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
por: Atanackovic, Lazar, et al.
Publicado: (2024)

Wasserstein Flow Matching: Generative modeling over families of distributions
por: Haviv, Doron, et al.
Publicado: (2024)

Geometry-Aware Normalizing Wasserstein Flows for Optimal Causal Inference
por: Hou, Kaiwen
Publicado: (2023)

Counterfactual Explanations via Riemannian Latent Space Traversal
por: Pegios, Paraskevas, et al.
Publicado: (2024)

Generalization and Optimization of SGD with Lookahead
por: Li, Kangcheng, et al.
Publicado: (2025)

Unveiling High-Probability Generalization in Decentralized SGD
por: Wang, Jiahuan, et al.
Publicado: (2026)

Contrastive Sequential Interaction Network Learning on Co-Evolving Riemannian Spaces
por: Sun, Li, et al.
Publicado: (2024)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
por: Gretton, Arthur, et al.
Publicado: (2026)

Bures-Wasserstein Flow Matching for Graph Generation
por: Jiang, Keyue, et al.
Publicado: (2025)

Mirror and Preconditioned Gradient Descent in Wasserstein Space
por: Bonet, Clément, et al.
Publicado: (2024)

DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
por: Wang, Yingxu, et al.
Publicado: (2026)

A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
por: Wang, Chenguang, et al.
Publicado: (2026)

An Explicit Surrogate for Gaussian Mixture Flow Matching with Wasserstein Gap Bounds
por: Rostami, Elham, et al.
Publicado: (2026)