Image de couverture de livre

Trade-offs in Data Memorization via Strong Data Processing Inequalities

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feldman, Vitaly, Kornowski, Guy, Lyu, Xin
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality
par: Wibisono, Andre
Publié: (2025)

Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimation
par: Nichani, Arjun, et autres
Publié: (2026)

Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity
par: Dudeja, Rishabh, et autres
Publié: (2022)

The Rate-Distortion-Perception Trade-off: The Role of Private Randomness
par: Hamdi, Yassine, et autres
Publié: (2024)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
par: Ye, Jiayuan, et autres
Publié: (2026)

Measures of Information Reflect Memorization Patterns
par: Bansal, Rachit, et autres
Publié: (2022)

Subsampling Suffices for Adaptive Data Analysis
par: Blanc, Guy
Publié: (2023)

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
par: Salgia, Sudeep, et autres
Publié: (2025)

Mixture-of-Experts under Finite-Rate Gating: Communication--Generalization Trade-offs
par: Khalesi, Ali, et autres
Publié: (2026)

Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences
par: Nuradha, Theshani, et autres
Publié: (2025)

Resolving Memorization in Empirical Diffusion Model for Manifold Data in High-Dimensional Spaces
par: Lyu, Yang, et autres
Publié: (2025)

Noise Quantification and Control in Circuits via Strong Data-Processing Inequalities
par: Sun, Chenyang
Publié: (2025)

Beyond Benign Overfitting in Nadaraya-Watson Interpolators
par: Barzilai, Daniel, et autres
Publié: (2025)

Efficient Agnostic Learning with Average Smoothness
par: Hanneke, Steve, et autres
Publié: (2023)

Strong Data Processing Inequalities and their Applications to Reliable Computation
par: Yang, Andrew K.
Publié: (2024)

The Oracle Complexity of Simplex-based Matrix Games
par: Kornowski, Guy, et autres
Publié: (2024)

Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
par: Madhabhavi, Bhavani A, et autres
Publié: (2024)

Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality
par: Wang, Shuchan, et autres
Publié: (2021)

Data-dependent Generalization Bounds via Variable-Size Compressibility
par: Sefidgaran, Milad, et autres
Publié: (2023)

Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
par: Liu, Yanxiao, et autres
Publié: (2026)

A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective
par: Ghodsi, Siamak, et autres
Publié: (2025)

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
par: Hamman, Faisal, et autres
Publié: (2023)

Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
par: Sefidgaran, Milad, et autres
Publié: (2025)

Efficient Generalization via Multimodal Co-Training under Data Scarcity and Distribution Shift
par: Pan, Tianyu Bell, et autres
Publié: (2025)

Efficient Personalization of Generative Models via Optimal Experimental Design
par: Schacht, Guy, et autres
Publié: (2025)

Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
par: Asi, Hilal, et autres
Publié: (2024)

Data-Driven Estimation of the False Positive Rate of the Bayes Binary Classifier via Soft Labels
par: Jeong, Minoh, et autres
Publié: (2024)

Optimal Sequential Recommendations: Exploiting User and Item Structure
par: Karzand, Mina, et autres
Publié: (2025)

Learning Causality for Longitudinal Data
par: Bouchattaoui, Mouad EL
Publié: (2025)

The Rough Topology for Numerical Data
par: Yiğit, Uğur
Publié: (2022)

Memorization-Compression Cycles Improve Generalization
par: Yu, Fangyuan
Publié: (2025)

Exact Recovery in the Data Block Model
par: Asadi, Amir R., et autres
Publié: (2026)

Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
par: Xiao, Shiji, et autres
Publié: (2026)

How Patterns Dictate Learnability in Sequential Data
par: Morawski, Mario, et autres
Publié: (2025)

Neural Polar Decoders for DNA Data Storage
par: Aharoni, Ziv, et autres
Publié: (2025)

Refining Labeling Functions with Limited Labeled Data
par: Li, Chenjie, et autres
Publié: (2025)

Application of Deep Learning in Biological Data Compression
par: Zou, Chunyu
Publié: (2025)

Differentially Private Bilevel Optimization
par: Kornowski, Guy
Publié: (2024)

Interpretive Efficiency: Information-Geometric Foundations of Data Usefulness
par: Katende, Ronald
Publié: (2025)

Online Clustering of Data Sequences with Bandit Information
par: Chandran, G Dhinesh, et autres
Publié: (2025)