arXiv Machine Learning
Iterating Consistency Models: Stability, Error Bounds and Noise Schedules
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Oct 12
Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning
arXiv:2610. 12865v1 Announce Type: new Abstract: Existing convergence guarantees for non-log-concave sampling with stochastic gradient Langevin Monte Carlo (SG-LMC) typically assume globally Lipschitz gradients and uniformly bounded noise variance.
arXiv Machine Learning
Oct 8
Universal Local Error and Realized Amplification for the First-Order EDM Predictor
arXiv:2610. 10190v1 Announce Type: cross Abstract: We analyze the first-order deterministic diffusion sampler of Karras et al.
arXiv Machine Learning
Oct 2
Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin Sampling
arXiv:2609.40193v1 Announce Type: new Abstract: We establish near-linear accuracy bounds for the classical Moreau--Yosida unadjusted Langevin algorithm (MYULA). The target is $\pi\propto e^{-f-g}$, w...
arXiv AI
Aug 12
SynBoost: A Synergistic Framework for Fast Sampling of Diffusion Models
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
arXiv Machine Learning
Sep 30
High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness
arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees ove...
arXiv Machine Learning
Jun 16
DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
arXiv:2606. 15359v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for planning and control by learning multimodal distributions over actions and trajectories.