Cover Image

On the Stability of Iterative Retraining of Generative Models on their own Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bertrand, Quentin, Bose, Avishek Joey, Duplessis, Alexandre, Jiralerspong, Marco, Gidel, Gauthier
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
by: Ferbach, Damien, et al.
Published: (2024)

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
by: Jiralerspong, Marco, et al.
Published: (2023)

General Causal Imputation via Synthetic Interventions
by: Jiralerspong, Marco, et al.
Published: (2024)

Omega: Optimistic EMA Gradients
by: Ramirez, Juan, et al.
Published: (2023)

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
by: Jiralerspong, Marco, et al.
Published: (2025)

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
by: Akhound-Sadegh, Tara, et al.
Published: (2024)

Expected flow networks in stochastic environments and two-player zero-sum games
by: Jiralerspong, Marco, et al.
Published: (2023)

Aligning Flow Map Policies with Optimal Q-Guidance
by: Ziakas, Christos, et al.
Published: (2026)

Coupling Models for One-Step Discrete Generation
by: Peng, Fred Zhangzhi, et al.
Published: (2026)

Fisher Flow Matching for Generative Modeling over Discrete Data
by: Davis, Oscar, et al.
Published: (2024)

Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
by: Davis, Oscar, et al.
Published: (2025)

The Superposition of Diffusion Models Using the Itô Density Estimator
by: Skreta, Marta, et al.
Published: (2024)

Self-Play Q-learners Can Provably Collude in the Iterated Prisoner's Dilemma
by: Bertrand, Quentin, et al.
Published: (2023)

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
by: Beznosikov, Aleksandr, et al.
Published: (2023)

RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
by: Yadav, Robin, et al.
Published: (2025)

Performative Prediction with Neural Networks
by: Mofakhami, Mehrnaz, et al.
Published: (2023)

Predicting Drug Effects from High-Dimensional, Asymmetric Drug Datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction
by: Bose, Avishek, et al.
Published: (2024)

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
by: Ferbach, Damien, et al.
Published: (2023)

Logarithmic-time Schedules for Scaling Language Models with Momentum
by: Ferbach, Damien, et al.
Published: (2026)

Scalable Equilibrium Sampling with Sequential Boltzmann Generators
by: Tan, Charlie B., et al.
Published: (2025)

Metric Flow Matching for Smooth Interpolations on the Data Manifold
by: Kapuśniak, Kacper, et al.
Published: (2024)

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
by: Schwinn, Leo, et al.
Published: (2024)

When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
by: Kim, Junhyung Lyle, et al.
Published: (2022)

MacroGuide: Topological Guidance for Macrocycle Generation
by: Maksymiuk, Alicja, et al.
Published: (2026)

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
by: Jiralerspong, Thomas, et al.
Published: (2026)

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
by: Dobre, David, et al.
Published: (2025)

Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
by: Rehman, Danyal, et al.
Published: (2025)

Unlearning-based Neural Interpretations
by: Choi, Ching Lam, et al.
Published: (2024)

Dimension-adapted Momentum Outscales SGD
by: Ferbach, Damien, et al.
Published: (2025)

In-Context Learning Can Re-learn Forbidden Tasks
by: Xhonneux, Sophie, et al.
Published: (2024)

Efficient Adversarial Training in LLMs with Continuous Attacks
by: Xhonneux, Sophie, et al.
Published: (2024)

Learning and Generalization with Mixture Data
by: Vardhan, Harsh, et al.
Published: (2025)

Planner Aware Path Learning in Diffusion Language Models Training
by: Peng, Fred Zhangzhi, et al.
Published: (2025)

Tight Lower Bounds and Improved Convergence in Performative Prediction
by: Khorsandi, Pedram, et al.
Published: (2024)

Path Planning for Masked Diffusion Model Sampling
by: Peng, Fred Zhangzhi, et al.
Published: (2025)

Curly Flow Matching for Learning Non-gradient Field Dynamics
by: Petrović, Katarina, et al.
Published: (2025)

LocalKMeans: Convergence of Lloyd's Algorithm with Distributed Local Iterations
by: Vardhan, Harsh, et al.
Published: (2025)

Reconstruct the Pruned Model without Any Retraining
by: Wang, Pingjie, et al.
Published: (2024)

Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
by: Schwinn, Leo, et al.
Published: (2025)

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
by: Jiralerspong, Thomas, et al.
Published: (2026)