Image de couverture de livre

How Scale Breaks "Normalized Stress" and KL Divergence: Rethinking Quality Metrics

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Smelser, Kiran, Gunaratne, Kaviru, Miller, Jacob, Kobourov, Stephen
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

"Normalized Stress" is Not Normalized: How to Interpret Stress Correctly
par: Smelser, Kiran, et autres
Publié: (2024)

Class Angular Distortion Index for Dimensionality Reduction
par: Gunaratne, Kaviru, et autres
Publié: (2026)

Bridging Graph Drawing and Dimensionality Reduction with Stochastic Stress Optimization
par: Hangan, Daniel, et autres
Publié: (2026)

Size Should not Matter: Scale-invariant Stress Metrics
par: Ahmed, Reyan, et autres
Publié: (2024)

Adaptive Symmetrization of the KL Divergence
par: Ben-Dov, Omri, et autres
Publié: (2025)

ENS-t-SNE: Embedding Neighborhoods Simultaneously t-SNE
par: Miller, Jacob, et autres
Publié: (2022)

On the KL-Divergence-based Robust Satisficing Model
par: Yan, Haojie, et autres
Publié: (2024)

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
par: Xie, Zhijie, et autres
Publié: (2022)

Training Neural Samplers with Reverse Diffusive KL Divergence
par: He, Jiajun, et autres
Publié: (2024)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
par: Yuan, Rui, et autres
Publié: (2026)

On Flow Matching KL Divergence
par: Su, Maojiang, et autres
Publié: (2025)

Optimal Stability of KL Divergence under Gaussian Perturbations
par: Pan, Jialu, et autres
Publié: (2026)

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
par: Aminian, Gholamali, et autres
Publié: (2025)

Rethinking Bregman Divergences in Kronecker-Factored Optimizers
par: Liu, Bing, et autres
Publié: (2026)

Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence
par: Datar, Adwait, et autres
Publié: (2025)

The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
par: Schaeffer, Bernardo P., et autres
Publié: (2025)

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
par: Zhu, Lingwei, et autres
Publié: (2023)

Scaling Context Requires Rethinking Attention
par: Gelada, Carles, et autres
Publié: (2025)

KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective
par: Muñoz, Andrés, et autres
Publié: (2026)

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
par: Zhang, Shiyuan, et autres
Publié: (2026)

Variational Approach for Efficient KL Divergence Estimation in Dirichlet Mixture Models
par: Pal, Samyajoy, et autres
Publié: (2024)

Rethinking Distance Metrics for Counterfactual Explainability
par: Williams, Joshua Nathaniel, et autres
Publié: (2024)

Visualization Tasks for Unlabeled Graphs
par: Oddo, Matt I. B., et autres
Publié: (2025)

Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks
par: Cinquin, Tristan, et autres
Publié: (2024)

UnitNorm: Rethinking Normalization for Transformers in Time Series
par: Huang, Nan, et autres
Publié: (2024)

Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization
par: Liu, Kezhao, et autres
Publié: (2025)

Using Reinforcement Learning to Optimize the Global and Local Crossing Number
par: Brand, Timo, et autres
Publié: (2025)

Tight Bounds on the Binomial CDF, and the Minimum of i.i.d Binomials, in terms of KL-Divergence
par: Zhu, Xiaohan, et autres
Publié: (2025)

Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Models
par: Yang, Kaylee Yingxi, et autres
Publié: (2022)

A Unified Framework for Rethinking Policy Divergence Measures in GRPO
par: Wu, Qingyuan, et autres
Publié: (2026)

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
par: Zhang, Yixian, et autres
Publié: (2025)

A Neural Network Algorithm for KL Divergence Estimation with Quantitative Error Bounds
par: Foss, Mikil, et autres
Publié: (2025)

Shifted Composition III: Local Error Framework for KL Divergence
par: Altschuler, Jason M., et autres
Publié: (2024)

State of the Art of Graph Visualization in non‐Euclidean Spaces
par: Jacob Miller, et autres
Publié: (2024)

Normalized Space Alignment: A Versatile Metric for Representation Analysis
par: Ebadulla, Danish, et autres
Publié: (2024)

Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
par: Kukreja, Dikshant, et autres
Publié: (2026)

Rethinking Evaluation Metric for Probability Estimation Models Using Esports Data
par: Choi, Euihyeon, et autres
Publié: (2023)

ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space
par: Yong, Shim Soon
Publié: (2025)

Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
par: Regenwetter, Lyle, et autres
Publié: (2023)

Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference
par: Han, Seungsu, et autres
Publié: (2025)