Image de couverture de livre

A theoretical basis for model collapse in recursive training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Borkar, Vivek Shripad
Format:	Preprint
Publié:	2025
Sujets:	Probability Machine Learning 68T01
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Stochastic approximation in non-markovian environments revisited
par: Borkar, Vivek Shripad
Publié: (2026)

Asymptotic convexity of wide and shallow neural networks
par: Borkar, Vivek, et autres
Publié: (2025)

Strategic inputs: feature selection from game-theoretic perspective
par: Zhao, Chi, et autres
Publié: (2025)

A ZeNN architecture to avoid the Gaussian trap
par: Carvalho, Luís, et autres
Publié: (2025)

The Positivity of the Neural Tangent Kernel
par: Carvalho, Luís, et autres
Publié: (2024)

Score Change of Variables
par: Robbins, Stephen
Publié: (2024)

Adynamical systems view of training generativemodels and the memorization phenomenon
par: Athreya, Siva, et autres
Publié: (2026)

Explainable post-training bias mitigation with distribution-based fairness metrics
par: Franks, Ryan, et autres
Publié: (2025)

Neural information field filter
par: Hao, Kairui, et autres
Publié: (2024)

The Selective G-Bispectrum and its Inversion: Applications to G-Invariant Networks
par: Mataigne, Simon, et autres
Publié: (2024)

A dynamic view of some anomalous phenomena in SGD
par: Borkar, Vivek Shripad
Publié: (2025)

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
par: Dadalto, Eduardo, et autres
Publié: (2023)

Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle
par: Tinker, Theodore Jerome, et autres
Publié: (2024)

AI-based modular warning machine for risk identification in proximity healthcare
par: Razzetta, Chiara, et autres
Publié: (2025)

Freeze, Diffuse, Decode: Geometry-Aware Adaptation of Pretrained Transformer Embeddings for Antimicrobial Peptide Design
par: Gawade, Pankhil, et autres
Publié: (2025)

Physics-Informed Neural Networks and Neural Operators for Parametric PDEs
par: Zhang, Zhuo, et autres
Publié: (2025)

Representation Integrity in Temporal Graph Learning Methods
par: Kooshafar, Elahe
Publié: (2025)

Differential Parity: Relative Fairness Between Two Sets of Decisions
par: Yu, Zhe, et autres
Publié: (2021)

ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators
par: Scassola, Davide, et autres
Publié: (2026)

On the Optimal Memorization Capacity of Transformers
par: Kajitsuka, Tokio, et autres
Publié: (2024)

Gradient Span Algorithms Make Predictable Progress in High Dimension
par: Benning, Felix, et autres
Publié: (2024)

Modeling Membrane Degradation in PEM Electrolyzers with Physics-Informed Neural Networks
par: Polo-Molina, Alejandro, et autres
Publié: (2025)

Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark
par: Yu, Zhiqi, et autres
Publié: (2026)

Optimal Bound for PCA with Outliers using Higher-Degree Voronoi Diagrams
par: Hashemian, Sajjad, et autres
Publié: (2024)

Classification by Separating Hypersurfaces: An Entropic Approach
par: Arratia, Argimiro, et autres
Publié: (2025)

Learning to Control the Smoothness of Graph Convolutional Network Features
par: Wang, Shih-Hsin, et autres
Publié: (2024)

Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning
par: Pan, Enze
Publié: (2026)

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks
par: Mandal, Saptarshi, et autres
Publié: (2024)

Stabilizing Machine Learning for Reproducible and Explainable Results: A Novel Validation Approach to Subject-Specific Insights
par: Vos, Gideon, et autres
Publié: (2024)

Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach
par: Zhang, Hao, et autres
Publié: (2024)

Statistical learning does not always entail knowledge
par: Díaz-Pachón, Daniel Andrés, et autres
Publié: (2024)

A Human-In-The-Loop Approach for Improving Fairness in Predictive Business Process Monitoring
par: Käppel, Martin, et autres
Publié: (2025)

seqme: a Python library for evaluating biological sequence design
par: Møller-Larsen, Rasmus, et autres
Publié: (2025)

Learning from Similarity-Confidence and Confidence-Difference
par: Tate, Tomoya, et autres
Publié: (2025)

Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes
par: Sugiyama, Kosuke, et autres
Publié: (2025)

The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
par: arXiv, Redacted by
Publié: (2026)

RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
par: Pan, Enze
Publié: (2026)

Learning from Complementary Features
par: Sugiyama, Kosuke, et autres
Publié: (2024)

Differentially Private Prototypes for Imbalanced Transfer Learning
par: Wahdany, Dariush, et autres
Publié: (2024)

Predictors of disease outbreaks at continentalscale in the African region: Insights and predictions with geospatial artificial intelligence using earth observations and routine disease surveillance data
par: Pezanowski, Scott, et autres
Publié: (2024)