Imagen de Portada

Constant Metric Scaling in Riemannian Computation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	You, Kisung
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Particle-Flow Algorithm for Free-Support Wasserstein Barycenters
por: You, Kisung
Publicado: (2025)

Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis
por: You, Kisung
Publicado: (2026)

Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy
por: You, Kisung
Publicado: (2026)

Semantics at an Angle: When Cosine Similarity Works Until It Doesn't
por: You, Kisung
Publicado: (2025)

Quotient-Based Posterior Analysis for Euclidean Latent Space Models
por: You, Kisung, et al.
Publicado: (2026)

PCA, SVD, and Centering of Data
por: Kim, Donggun, et al.
Publicado: (2023)

Network Distance Based on Laplacian Flows on Graphs
por: Bao, Dianbin, et al.
Publicado: (2018)

Learning over von Mises-Fisher Distributions via a Wasserstein-like Geometry
por: You, Kisung, et al.
Publicado: (2025)

Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics
por: Yu, Hanlin, et al.
Publicado: (2023)

Scalable Geometric Learning with Correlation-Based Functional Brain Networks
por: You, Kisung, et al.
Publicado: (2025)

Finite Mixture Modeling with Riemannian Gaussian Distributions on Hyperbolic Space
por: You, Kisung
Publicado: (2026)

Riemannian Laplace Approximation with the Fisher Metric
por: Yu, Hanlin, et al.
Publicado: (2023)

OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
por: Lou, Yuxuan, et al.
Publicado: (2026)

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
por: Yu, Peilin, et al.
Publicado: (2025)

What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
por: Azeglio, Simone, et al.
Publicado: (2025)

Computational Sentence-level Metrics Predicting Human Sentence Comprehension
por: Sun, Kun, et al.
Publicado: (2024)

Dual Riemannian Newton Method on Statistical Manifolds
por: Zhou, Derun, et al.
Publicado: (2025)

Scale selection for geometric medians on product manifolds
por: You, Kisung
Publicado: (2026)

Riemannian Principal Component Analysis
por: Rodríguez, Oldemar
Publicado: (2025)

Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation
por: Cai, Yang, et al.
Publicado: (2023)

A Riemannian Approach to Ground Metric Learning for Optimal Transport
por: Jawanpuria, Pratik, et al.
Publicado: (2024)

Inversion-Free Natural Gradient Descent on Riemannian Manifolds
por: Draca, Dario, et al.
Publicado: (2026)

Softmax Attention with Constant Cost per Token
por: Heinsen, Franz A.
Publicado: (2024)

Constant Bit-size Transformers Are Turing Complete
por: Li, Qian, et al.
Publicado: (2025)

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
por: Krajewski, Jakub, et al.
Publicado: (2025)

Test-Time Scaling Makes Overtraining Compute-Optimal
por: Roberts, Nicholas, et al.
Publicado: (2026)

Resolving Discrepancies in Compute-Optimal Scaling of Language Models
por: Porian, Tomer, et al.
Publicado: (2024)

Fast Riemannian-manifold Hamiltonian Monte Carlo for hierarchical Gaussian-process models
por: Hayakawa, Takashi, et al.
Publicado: (2025)

Large Scale Training of Graph Neural Networks for Optimal Markov-Chain Partitioning Using the Kemeny Constant
por: Martino, Sam Alexander, et al.
Publicado: (2023)

Sampling from multi-modal distributions on Riemannian manifolds with training-free stochastic interpolants
por: Durmus, Alain, et al.
Publicado: (2026)

Scaling Test-Time Compute Without Verification or RL is Suboptimal
por: Setlur, Amrith, et al.
Publicado: (2025)

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
por: Snell, Charlie, et al.
Publicado: (2024)

Quantization-based Bounds on the Wasserstein Metric
por: Bobrutsky, Jonathan, et al.
Publicado: (2025)

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
por: Xu, Zukang, et al.
Publicado: (2025)

Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
por: London, Charles, et al.
Publicado: (2025)

Cross-Scale Reservoir Computing for large spatio-temporal forecasting and modeling
por: Alboré, Nicola, et al.
Publicado: (2025)

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching
por: Miao, Fangran, et al.
Publicado: (2026)

Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction
por: Demidovich, Yury, et al.
Publicado: (2024)

Metric Compatible Training for Online Backfilling in Large-Scale Retrieval
por: Seo, Seonguk, et al.
Publicado: (2023)

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
por: Béthune, Louis, et al.
Publicado: (2025)