Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport

• URL: http://arxiv.org/abs/2609.11842v1
• Date: Thu, 10 Sep 2026 17:30:44 GMT
• Title: Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
• Abstract summary: Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths.<n>We introduce a model-aware schedule construction based on fiberwise optimal transport.<n>We evaluate DDPMs and flow matching across prediction targets, training configurations, risk-estimation checkpoints, datasets, and architectures.
• Score: 1.1014388269312267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain strong baselines but remains model-agnostic and ignores prediction error. Here we introduce a model-aware schedule construction based on fiberwise optimal transport. At a fixed time and state on the probability path, compatible signal/noise decompositions form an affine fiber. We define a fiberwise prediction risk by averaging optimal-transport costs between the true and predictor-induced decompositions within these fibers. On a fixed coefficient curve, combining this risk with coefficient-path kinetic action yields a closed-form optimal time allocation. This construction extends to general linear prediction targets, and the risk profile can be estimated from an early baseline checkpoint. We evaluate DDPMs and flow matching across prediction targets, training configurations, risk-estimation checkpoints, datasets, and architectures. Our model-aware schedules consistently outperform strong baselines, including a 38.6% relative FID reduction for flow matching on CIFAR-10 at 16 function evaluations. Each model-agnostic kinetic baseline determines its own kinetic reference coordinate. In these coordinates, fiberwise-risk profiles from independently trained models in different settings align closely after normalization to unit area. The resulting schedule deformations used in training also align, suggesting empirical universality across the evaluated models and settings. Pretrained-checkpoint diagnostics extend this normalized-risk agreement to larger conditional latent diffusion and 2-RF models. A frozen analytic allocation template retains most of the model-aware improvement without further risk estimation or model-specific fitting.

Related papers

• Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models [0.0]
  Many machine-learning weather models (MLWMs) are deterministic, producing a single forecast with no estimate of its own uncertainty.<n>A growing family of trained-probabilistic models generate calibrated ensembles directly, at the price of a dedicated training run.<n>We ask how much uncertainty can be extracted from a deterministic checkpoint that already exists, without retraining it.
  arXiv  Detail & Related papers  (2026-09-08T08:18:40Z)
• A Defense of the Quadratic Model [71.57026347416729]
  We stress test the simplest possible model of optimization -- the quadratic model.<n>We show that it can be predictive surprisingly in an LLM setting with 150M parameters and 3B training tokens.
  arXiv  Detail & Related papers  (2026-07-23T18:02:03Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Curvature-Guided LoRA: Steering in the pretrained NTK subspace [60.35296431630704]
  We introduce the prediction alignment problem, aiming to match the predictor obtained via PEFT to that of full fine-tuning at the level of outputs.<n>We show that this objective naturally leads to a curvature-aware, second-order formulation, where optimal low-rank updates correspond to a Newton-like, curvature-whitened gradient.<n>Based on this insight, we propose Curvature-Guided LoRA (CG-LoRA), which selects and scales adaptation directions using local curvature information.
  arXiv  Detail & Related papers  (2026-03-31T14:46:39Z)
• Self-Flow-Matching assisted Full Waveform Inversion [10.422441176688597]
  Full-waveform inversion (FWI) is a high-resolution seismic imaging method that estimates subsurface velocity by matching simulated and recorded waveforms.<n>FWI is highly nonlinear, prone to cycle skipping, and sensitive to noise.<n>We introduce Self-Flow-Matching assisted Full-Waveform Inversion (SFM-FWI), a physics-driven framework that eliminates the need for large-scale offline pretraining.
  arXiv  Detail & Related papers  (2026-03-13T02:10:01Z)
• Differentiable Stochastic Traffic Dynamics: Physics-Informed Generative Modelling in Transportation [0.0]
  This work develops a framework in which the physics constraint itself is distributional and spatial, derived from traffic-flow dynamics.<n>The framework provides a basis for distributional traffic-state estimation and for fundamental analysis in a physics-informed generative setting.
  arXiv  Detail & Related papers  (2026-03-10T04:25:20Z)
• Adaptive Conformal Prediction Intervals Over Trajectory Ensembles [50.31074512684758]
  Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling.<n>We propose a unified framework based on conformal prediction that transforms sampled trajectories into calibrated prediction intervals with theoretical coverage guarantees.
  arXiv  Detail & Related papers  (2025-08-18T21:14:07Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• An Adaptive Framework for Autoregressive Forecasting in CFD Using Hybrid Modal Decomposition and Deep Learning [3.1337872355726084]
  This work presents, to the best of the authors' knowledge, the first generalizable and fully data-driven adaptive framework designed to stabilize deep learning (DL) autoregressive forecasting models over long time horizons.<n>The proposed methodology alternates between two phases: (i) predicting the evolution of the flow field over a selected time interval using a trained DL model, and (ii) updating the model with newly generated CFD data when stability degrades, thus maintaining accurate long-term forecasting.<n>The framework is validated across three increasingly complex flow regimes, from laminar to turbulent, demonstrating from 30 % to 95
  arXiv  Detail & Related papers  (2025-05-02T18:33:41Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)
• Active Learning with Multifidelity Modeling for Efficient Rare Event Simulation [0.0]
  We propose a framework for active learning with multifidelity modeling emphasizing the efficient estimation of rare events. Our framework works by fusing a low-fidelity (LF) prediction with an HF-inferred correction, filtering the corrected LF prediction to decide whether to call the high-fidelity model. For improved robustness when estimating smaller failure probabilities, we propose using dynamic active learning functions that decide when to call the HF model.
  arXiv  Detail & Related papers  (2021-06-25T17:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.