Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
read the original abstract
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant $n$-body particle systems. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5\times$ faster, which allows it to be the first method to train using energy on the challenging $55$-particle Lennard-Jones system.
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
Variational Inference via Entropic Transport Descent
ETD derives particle updates in ParVI from the JKO scheme lifted to couplings and relaxed by KL chain rule, reducing each step to Sinkhorn and showing gains over SVGD in high-dim and multimodal tests.
-
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
The Laplace-Fisher Gate Identity supplies the variance-optimal matrix gate for blended score estimation under Ornstein-Uhlenbeck diffusion and yields improved normalized posterior-density surrogates from MCMC pilot sa...
-
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
The Laplace-Fisher Gate Identity supplies the variance-optimal matrix blending coefficients for Tweedie and target-score estimators under an OU diffusion, enabling improved finite-reference score estimation and poster...
-
Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and...
-
Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Free Energy Surface Sampling via Reduced Flow Matching
FES-FM applies reduced flow matching with a Hessian-derived prior to directly sample free energy surfaces in collective variable space, claiming lower computational cost and higher accuracy per unit time than standard...
-
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Tempered sequential Monte Carlo samples from a Boltzmann-tilted distribution over controllers to optimize trajectories and policies under differentiable dynamics.
-
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Tempered sequential Monte Carlo samples efficiently from a temperature-annealed distribution over controller parameters to solve trajectory and policy optimization under differentiable dynamics.
-
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
ALGD augments the Lagrangian to locally convexify the energy landscape in diffusion models, stabilizing safe RL training and generation without changing optimal policies.
-
Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and a...
-
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.