Copertina

Exponential families from a single KL identity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Dymetman, Marc
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Information Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Binary Rewards and Reinforcement Learning: Fundamental Challenges
di: Dymetman, Marc
Pubblicazione: (2026)

Exponential convergence rate for Iterative Markovian Fitting
di: Sokolov, Kirill, et al.
Pubblicazione: (2025)

On the Exponential Convergence for Offline RLHF with Pairwise Comparisons
di: Chen, Zhirui, et al.
Pubblicazione: (2024)

A Neural Network Algorithm for KL Divergence Estimation with Quantitative Error Bounds
di: Foss, Mikil, et al.
Pubblicazione: (2025)

Divergences induced by dual subtractive and divisive normalizations of exponential families and their convex deformations
di: Nielsen, Frank
Pubblicazione: (2023)

Exponentially Consistent Nonparametric Linkage-Based Clustering of Data Sequences
di: Singh, Bhupender, et al.
Pubblicazione: (2024)

Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection
di: Cichocki, Andrzej, et al.
Pubblicazione: (2024)

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
di: Zhao, Qingyue, et al.
Pubblicazione: (2026)

Testing with Non-identically Distributed Samples
di: Garg, Shivam, et al.
Pubblicazione: (2023)

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
di: Puranik, Bhagyashree, et al.
Pubblicazione: (2023)

Measuring the Intrinsic Dimension of Earth Representations
di: Rao, Arjun, et al.
Pubblicazione: (2025)

Foundational theories of hesitant fuzzy sets and families of hesitant fuzzy sets
di: Lu, Shizhan, et al.
Pubblicazione: (2023)

Certifying almost all quantum states with few single-qubit measurements
di: Huang, Hsin-Yuan, et al.
Pubblicazione: (2024)

Momentum Accelerates Evolutionary Dynamics
di: Harper, Marc, et al.
Pubblicazione: (2020)

Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
di: Liu, Hang, et al.
Pubblicazione: (2025)

Exponential quantum advantage in processing massive classical data
di: Zhao, Haimeng, et al.
Pubblicazione: (2026)

Conditional Dependence via U-Statistics Pruning
di: de Cabrera, Ferran, et al.
Pubblicazione: (2024)

Getting Free Bits Back from Rotational Symmetries in LLMs
di: He, Jiajun, et al.
Pubblicazione: (2024)

Learning from Many and Adapting to the Unknown in Open-set Test Streams
di: Zhang, Xiao, et al.
Pubblicazione: (2026)

Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective
di: Langer, Carlotta, et al.
Pubblicazione: (2024)

Learning Regularities from Data using Spiking Functions: A Theory
di: Zhang, Canlin, et al.
Pubblicazione: (2024)

Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
di: Mazumdar, Arya, et al.
Pubblicazione: (2025)

Information-directed sampling for bandits: a primer
di: Hirling, Annika, et al.
Pubblicazione: (2025)

Heterogeneity Matters even More in Distributed Learning: Study from Generalization Perspective
di: Kavian, Masoud, et al.
Pubblicazione: (2025)

Dynamic Feature Selection from Variable Feature Sets Using Features of Features
di: Takahashi, Katsumi, et al.
Pubblicazione: (2025)

How Big Should a Wireless Foundation Model Be?
di: Cheng, Wei-Lun, et al.
Pubblicazione: (2026)

A unified framework for learning with nonlinear model classes from arbitrary linear samples
di: Adcock, Ben, et al.
Pubblicazione: (2023)

Two tales for a geometric Jensen--Shannon divergence
di: Nielsen, Frank
Pubblicazione: (2025)

Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!
di: Sefidgaran, Milad, et al.
Pubblicazione: (2023)

Learning Capacity: A Measure of the Effective Dimensionality of a Model
di: Chen, Daiwei, et al.
Pubblicazione: (2023)

How Does Attention Help? Insights from Random Matrices on Signal Recovery from Sequence Models
di: Seddik, Mohamed El Amine
Pubblicazione: (2026)

Outlier Detection of Poisson-Distributed Targets Using a Seabed Sensor Network
di: Kim, Mingyu, et al.
Pubblicazione: (2025)

VALID: a Validated Algorithm for Learning in Decentralized Networks with Possible Adversarial Presence
di: Bakshi, Mayank, et al.
Pubblicazione: (2024)

Refined Differentially Private Linear Regression via Extension of a Free Lunch Result
di: S, Sasmita Harini, et al.
Pubblicazione: (2026)

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
di: Zhao, Yan, et al.
Pubblicazione: (2026)

Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the Future
di: Noël, Pierre-André
Pubblicazione: (2026)

Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
di: Liu, Yanxiao, et al.
Pubblicazione: (2026)

Causal Reasoning: Charting a Revolutionary Course for Next-Generation AI-Native Wireless Networks
di: Thomas, Christo Kurisummoottil, et al.
Pubblicazione: (2023)

Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians by Application of the Bayes Codes for Context Tree Models
di: Nakahara, Yuta
Pubblicazione: (2024)

Overfitting has a limitation: a model-independent generalization gap bound based on Rényi entropy
di: Suzuki, Atsushi, et al.
Pubblicazione: (2025)