REVIEW 6 cited by
Heavy-Tailed Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditional diffusion and flow-matching models with standard Gaussian priors fail to capture heavy-tailed behavior. We address this by repurposing the diffusion framework for heavy-tail estimation using multivariate Student-t distributions. We develop a tailored perturbation kernel and derive the denoising posterior based on the conditional Student-t distribution for the backward process. Inspired by $\gamma$-divergence for heavy-tailed distributions, we derive a training objective for heavy-tailed denoisers. The resulting framework introduces controllable tail generation using only a single scalar hyperparameter, making it easily tunable for diverse real-world distributions. As specific instantiations of our framework, we introduce t-EDM and t-Flow, extensions of existing diffusion and flow models that employ a Student-t prior. Remarkably, our approach is readily compatible with standard Gaussian diffusion models and requires only minimal code changes. Empirically, we show that our t-EDM and t-Flow outperform standard diffusion models in heavy-tail estimation on high-resolution weather datasets in which generating rare and extreme events is crucial.
Forward citations
Cited by 6 Pith papers
-
An Extreme Value Perspective on Learning Stress Laws
SS-GEN splices an explicit radial tail law with a DGM-learned angular law so standard generative models produce asymptotically exact multivariate extremes and rare-event probabilities beyond the data.
-
Denoising Subordinated Probabilistic Models: Diffusion with a Tempered-Stable Volatility Clock, and What the Noise Mechanism Actually Controls
Heavy-tailed noise in diffusion can be exactly calibrated via a tempered-stable volatility chain, but is provably a nuisance whenever the denoiser sees it and the chain is drawn independently of the data.
-
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
Variance-corrective time shifting cancels the variance inflation of naive temperature sampling so pretrained diffusion models can raise diversity without retraining.
-
Heavy-Tailed Flow Matching via Random Clocks
HTFM trains flow-matching models with heavy-tailed source distributions obtained by mixing Gaussian sources over a random clock path, improving tail-statistic recovery and low-NFE sampling.
-
Offline Reinforcement Learning with Penalized Action Noise Injection
Injecting noise-perturbed actions into offline Q-learning with a distance penalty improves D4RL performance over IQL and TD3 baselines, formalized as Q-learning in a Noisy Action MDP.
-
Perspectives on Tsallis Statistics for Artificial Intelligence
Independent AI methods, including sparsemax attention, Tsallis-entropy reinforcement learning, Student-t generative models, and robust losses, are instances of a single 'q-dial' deformation of Boltzmann-Gibbs statisti...
Discussion (0). Sign in to comment.