When Does Model Collapse Occur in Structured Interactive Learning?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Yuchen, Zhou, Kangjie, Su, Weijie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Tractability from overparametrization: The example of the negative perceptron
di: Montanari, Andrea, et al.
Pubblicazione: (2021)

A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
di: Su, Weijie J.
Pubblicazione: (2024)

A statistical theory of overfitting for imbalanced classification
di: Lyu, Jingyang, et al.
Pubblicazione: (2025)

Optimal Convergence Analysis of DDPM for General Distributions
di: Jiao, Yuchen, et al.
Pubblicazione: (2025)

Learning single index model with gradient descent: spectral initialization and precise asymptotics
di: Chen, Yuchen, et al.
Pubblicazione: (2025)

You Are the Best Reviewer of Your Own Papers: The Isotonic Mechanism
di: Su, Weijie
Pubblicazione: (2022)

Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
di: Li, Gen, et al.
Pubblicazione: (2025)

Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
di: Garg, Anvit, et al.
Pubblicazione: (2025)

Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA
di: Zhou, Yuchen, et al.
Pubblicazione: (2023)

Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
di: Li, Xiang, et al.
Pubblicazione: (2025)

Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent
di: Patil, Pratik, et al.
Pubblicazione: (2024)

Interactive Learning of Single-Index Models via Stochastic Gradient Descent
di: Rajaraman, Nived, et al.
Pubblicazione: (2026)

Higher-Order Causal Structure Learning with Additive Models
di: Enouen, James, et al.
Pubblicazione: (2025)

Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
di: Paik, Seunghoon, et al.
Pubblicazione: (2025)

Transformers Meet In-Context Learning: A Universal Approximation Theory
di: Li, Gen, et al.
Pubblicazione: (2025)

Isotonic Mechanism for Exponential Family Estimation in Machine Learning Peer Review
di: Yan, Yuling, et al.
Pubblicazione: (2023)

From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
di: Bakshi, Soham, et al.
Pubblicazione: (2026)

Faster Diffusion Models via Higher-Order Approximation
di: Li, Gen, et al.
Pubblicazione: (2025)

Interaction Screening and Pseudolikelihood Approaches for Tensor Learning in Ising Models
di: Liu, Tianyu, et al.
Pubblicazione: (2023)

Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
di: Zucker, Shai, et al.
Pubblicazione: (2025)

Learning Linear Polytree Structural Equation Models
di: Lou, Xingmei, et al.
Pubblicazione: (2021)

Structured Prediction in Online Learning
di: Boudart, Pierre, et al.
Pubblicazione: (2024)

Robust Detection of Watermarks for Large Language Models Under Human Edits
di: Li, Xiang, et al.
Pubblicazione: (2024)

When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling
di: Wen, Garrett G., et al.
Pubblicazione: (2025)

Towards a unified framework for guided diffusion models
di: Jiao, Yuchen, et al.
Pubblicazione: (2025)

Adaptive Split Balancing for Optimal Random Forest
di: Zhang, Yuqian, et al.
Pubblicazione: (2024)

Wasserstein Transfer Learning
di: Zhang, Kaicheng, et al.
Pubblicazione: (2025)

When Are Trade-Off Functions Testable from Finite Samples?
di: Shi, Kaining, et al.
Pubblicazione: (2026)

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
di: Wu, Jingda, et al.
Pubblicazione: (2026)

Local Minima Structures in Gaussian Mixture Models
di: Chen, Yudong, et al.
Pubblicazione: (2020)

General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions
di: Li, Yicheng
Pubblicazione: (2026)

When Does Bottom-up Beat Top-down in Hierarchical Community Detection?
di: Dreveton, Maximilien, et al.
Pubblicazione: (2023)

Shifted Interpolation for Differential Privacy
di: Bok, Jinho, et al.
Pubblicazione: (2024)

Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
di: Jiao, Yuchen, et al.
Pubblicazione: (2025)

Algebraic Geometrical Analysis of Metropolis Algorithm When Parameters Are Non-identifiable
di: Nagata, Kenji, et al.
Pubblicazione: (2024)

Estimation of Models with Limited Data by Leveraging Shared Structure
di: Rui, Maryann, et al.
Pubblicazione: (2023)

What Functions Does XGBoost Learn?
di: Ki, Dohyeong, et al.
Pubblicazione: (2026)

When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
di: Flynn, Donald, et al.
Pubblicazione: (2026)

Stochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data
di: Rice, James
Pubblicazione: (2026)

High-dimensional Clustering and Signal Recovery under Block Signals
di: Su, Wu, et al.
Pubblicazione: (2025)