Tilt Matching for Scalable Sampling and Fine-Tuning

• URL: http://arxiv.org/abs/2512.21829v1
• Date: Fri, 26 Dec 2025 02:12:10 GMT
• Title: Tilt Matching for Scalable Sampling and Fine-Tuning
• Authors: Peter Potaptchik, Cheuk-Kit Lee, Michael S. Albergo,
• Abstract summary: We propose a scalable algorithm for using interpolants to sample from unnormalized densities and for fine-tuning generative models.<n>The approach, Tilt Matching, arises from a dynamical equation relating the flow matching velocity to one targeting the same distribution tilted by a reward.<n>We empirically verify that the approach is efficient and highly scalable, providing state-of-the-art results on sampling under Lennard-Jones potentials and is competitive on fine-tuning Stable Diffusion.
• Score: 4.14348726233299
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching, arises from a dynamical equation relating the flow matching velocity to one targeting the same distribution tilted by a reward, implicitly solving a stochastic optimal control problem. The new velocity inherits the regularity of stochastic interpolant transports while also being the minimizer of an objective with strictly lower variance than flow matching itself. The update to the velocity field can be interpreted as the sum of all joint cumulants of the stochastic interpolant and copies of the reward, and to first order is their covariance. The algorithms do not require any access to gradients of the reward or backpropagating through trajectories of the flow or diffusion. We empirically verify that the approach is efficient and highly scalable, providing state-of-the-art results on sampling under Lennard-Jones potentials and is competitive on fine-tuning Stable Diffusion, without requiring reward multipliers. It can also be straightforwardly applied to tilting few-step flow map models.

Related papers

• Temporal Pair Consistency for Variance-Reduced Flow Matching [13.328987133593154]
  Temporal Pair Consistency (TPC) is a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path.<n>Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions.
  arXiv  Detail & Related papers  (2026-02-04T00:05:21Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Test-time scaling of diffusions with flow maps [68.79792714591564]
  A common recipe to improve diffusion models at test-time is to introduce the gradient of the reward into the dynamics of the diffusion itself.<n>We propose a simple solution by working directly with a flow map.<n>By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods.
  arXiv  Detail & Related papers  (2025-11-27T18:44:12Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Consistency Flow Matching: Defining Straight Flows with Velocity Consistency [97.28511135503176]
  We introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models.
  arXiv  Detail & Related papers  (2024-07-02T16:15:37Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions [18.299322342860517]
  A class of generative models that unifies flow-based and diffusion-based methods is introduced.<n>These models extend the framework proposed in Albergo and VandenEijnden (2023), enabling the use of a broad class of continuous-time processes called interpolants.
  arXiv  Detail & Related papers  (2023-03-15T17:43:42Z)
• Building Normalizing Flows with Stochastic Interpolants [11.22149158986164]
  A simple generative quadratic model based on a continuous-time normalizing flow between any pair of base and target distributions is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent distribution that interpolates between the base and the target in finite time.
  arXiv  Detail & Related papers  (2022-09-30T16:30:31Z)
• A Stochastic Newton Algorithm for Distributed Convex Optimization [62.20732134991661]
  We analyze a Newton algorithm for homogeneous distributed convex optimization, where each machine can calculate gradients of the same population objective. We show that our method can reduce the number, and frequency, of required communication rounds compared to existing methods without hurting performance.
  arXiv  Detail & Related papers  (2021-10-07T17:51:10Z)
• Explicit Regularization of Stochastic Gradient Methods through Duality [9.131027490864938]
  We propose randomized Dykstra-style algorithms based on randomized dual coordinate ascent. For accelerated coordinate descent, we obtain a new algorithm that has better convergence properties than existing gradient methods in the interpolating regime.
  arXiv  Detail & Related papers  (2020-03-30T20:44:56Z)
• Gaussianization Flows [113.79542218282282]
  We propose a new type of normalizing flow model that enables both efficient iteration of likelihoods and efficient inversion for sample generation. Because of this guaranteed expressivity, they can capture multimodal target distributions without compromising the efficiency of sample generation.
  arXiv  Detail & Related papers  (2020-03-04T08:15:06Z)
• Stochastic Normalizing Flows [2.323220706791067]
  We show that normalizing flows can be used to learn the transformation of a simple prior distribution. We derive an efficient training procedure by which both the sampler's and the flow's parameters can be optimized end-to-end. We illustrate the representational power, sampling efficiency and correctness of SNFs on several benchmarks including applications to molecular sampling systems in equilibrium.
  arXiv  Detail & Related papers  (2020-02-16T23:29:32Z)

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.