Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.
Cambridge University Press
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
AutoRedTrader generates synthetic financial misinformation via behavioral bias manipulation and agent feedback to red-team LLM trading agents, reaching 69% exposure and 26.67% attack success on Bitcoin data simulations.
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
PSD kernel densities give a convex MCAR imputer with closed-form marginals, KL consistency rates that adapt to smoothness, and competitive energy-distance performance on small real tables.
Task information structure determines ML scaling success, with code's dense verifiable signals enabling predictable progress while sparse-feedback tasks like typical RL do not.
citing papers explorer
-
An exact information theory of generalization phase transitions in Bayesian diffusion models
Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.
-
AutoRedTrader: Autonomous Red Teaming of Trading Agents through Synthetic Misinformation Injection
AutoRedTrader generates synthetic financial misinformation via behavioral bias manipulation and agent feedback to red-team LLM trading agents, reaching 69% exposure and 26.67% attack success on Bitcoin data simulations.
-
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
-
Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation
PSD kernel densities give a convex MCAR imputer with closed-form marginals, KL consistency rates that adapt to smoothness, and competitive energy-distance performance on small real tables.
-
Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning
Task information structure determines ML scaling success, with code's dense verifiable signals enabling predictable progress while sparse-feedback tasks like typical RL do not.