REVIEW 10 cited by
Path Integral Sampler: a stochastic control approach for sampling
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
read the original abstract
We present Path Integral Sampler~(PIS), a novel algorithm to draw samples from unnormalized probability density functions. The PIS is built on the Schr\"odinger bridge problem which aims to recover the most likely evolution of a diffusion process given its initial distribution and terminal distribution. The PIS draws samples from the initial distribution and then propagates the samples through the Schr\"odinger bridge to reach the terminal distribution. Applying the Girsanov theorem, with a simple prior diffusion, we formulate the PIS as a stochastic optimal control problem whose running cost is the control energy and terminal cost is chosen according to the target distribution. By modeling the control as a neural network, we establish a sampling algorithm that can be trained end-to-end. We provide theoretical justification of the sampling quality of PIS in terms of Wasserstein distance when sub-optimal control is used. Moreover, the path integrals theory is used to compute importance weights of the samples to compensate for the bias induced by the sub-optimality of the controller and time-discretization. We experimentally demonstrate the advantages of PIS compared with other start-of-the-art sampling methods on a variety of tasks.
Forward citations
Cited by 10 Pith papers
-
Sample complexity of Schr\"odinger potential estimation
An empirical KL minimizer over log-potentials estimates Schrödinger bridge potentials with terminal excess KL risk O(log^2 n / n) in the realizable case, even when the target distribution has unbounded support.
-
Stochastic Quantization as Optimal Control
Stochastic quantization is re-expressed as finite-time optimal control, in which a learned Doob force plus exact path weights reach the Gibbs measure without waiting for equilibrium.
-
Solving Inverse Problems with Flow-based Models via Model Predictive Control
MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.
-
Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior
Feynman-Kac particle steering, previously diffusion-only, is derived for conditional flow matching and used to generate chirality-correct chemical transition states.
-
Path Integral Optimiser: Global Optimisation via Neural Schr\"odinger-F\"ollmer Diffusion
A neural Schrödinger-Föllmer diffusion, trained like the Path Integral Sampler, is repurposed as a global optimizer, with new conditional convergence bounds and competitive results on small tasks only.
-
Aligning Protein Conformation Ensemble Generation with Physical Feedback
EBA fine-tunes a protein diffusion model by reweighting sampled conformations according to their force-field energies, improving ensemble realism on the ATLAS benchmark.
-
Amortized In-Context Bayesian Posterior Estimation
A benchmark of in-context Bayesian posterior estimators shows the reverse-KL objective with transformers and normalizing flows outperforms forward-KL neural posterior estimation on predictive and out-of-distribution tasks.
-
Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling
A train-then-correct Hamiltonian Monte Carlo with learned stochastic paths gives exact Boltzmann corrections via a recorded generalized work, with limited but honest empirical validation.
-
Continuously Tempered Diffusion Samplers
CTDS trains neural samplers with a controlled Langevin dynamics over both position and a continuous temperature coordinate, and reports improved sampling on a 40-mode Gaussian mixture.
-
Neural Flow Samplers with Shortcut Models
Neural Flow Shortcut Sampler (NFS2) estimates the partition-function derivative with velocity-driven SMC and Stein control variates, and adds a generalized shortcut consistency loss for few-step sampling.
Discussion (0). Continue with ORCID to comment.