Higher-variance classes are learned first in diffusion models; strong class imbalance reverses the order and imposes distinct delayed learning times on minority classes.
The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability.arXiv preprint arXiv:2310.17467
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
stat.ML 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.
Proposes SDE sampler with state-dependent diffusion for HTDMs that induces self-regulating annealing, claimed necessary for heavy-tailed sampling.
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.
citing papers explorer
-
The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
Higher-variance classes are learned first in diffusion models; strong class imbalance reverses the order and imposes distinct delayed learning times on minority classes.
-
Flowing with Confidence
FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.
-
Self-Regulating Annealing in Heavy-Tailed Diffusion Models
Proposes SDE sampler with state-dependent diffusion for HTDMs that induces self-regulating annealing, claimed necessary for heavy-tailed sampling.
-
Statistical Properties of Training & Generalization
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.