Accelerating Particle-based Energetic Variational Inference

• URL: http://arxiv.org/abs/2504.03158v1
• Date: Fri, 04 Apr 2025 04:31:19 GMT
• Title: Accelerating Particle-based Energetic Variational Inference
• Authors: Xuelian Bao, Lulu Kang, Chun Liu, Yiwei Wang,
• Abstract summary: We propose a particle-based variational inference (ParVI) method that accelerates the EVI-Im.<n>Inspired by energy quadratization (EQ) and operator splitting techniques for gradient flows, our approach efficiently drives particles towards the target distribution.
• Score: 5.618322163107168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose a novel particle-based variational inference (ParVI) method that accelerates the EVI-Im. Inspired by energy quadratization (EQ) and operator splitting techniques for gradient flows, our approach efficiently drives particles towards the target distribution. Unlike EVI-Im, which employs the implicit Euler method to solve variational-preserving particle dynamics for minimizing the KL divergence, derived using a "discretize-then-variational" approach, the proposed algorithm avoids repeated evaluation of inter-particle interaction terms, significantly reducing computational cost. The framework is also extensible to other gradient-based sampling techniques. Through several numerical experiments, we demonstrate that our method outperforms existing ParVI approaches in efficiency, robustness, and accuracy.

Related papers

• Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment [81.84950252537618]
  This paper reveals a unified game-theoretic connection between iterative BOND and self-play alignment.<n>We establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized win rate dominance optimization.
  arXiv  Detail & Related papers  (2024-10-28T04:47:39Z)
• Semi-Implicit Functional Gradient Flow for Efficient Sampling [30.32233517392456]
  We propose a functional gradient ParVI method that uses perturbed particles with Gaussian noise as the approximation family.<n>We show that the corresponding functional gradient flow, which can be estimated via denoising score matching with neural networks, exhibits strong theoretical convergence guarantees.<n>In addition, we present an adaptive version of our method that automatically selects the appropriate noise magnitude during sampling.
  arXiv  Detail & Related papers  (2024-10-23T15:00:30Z)
• Sample-efficient Bayesian Optimisation Using Known Invariances [56.34916328814857]
  We show that vanilla and constrained BO algorithms are inefficient when optimising invariant objectives. We derive a bound on the maximum information gain of these invariant kernels. We use our method to design a current drive system for a nuclear fusion reactor, finding a high-performance solution.
  arXiv  Detail & Related papers  (2024-10-22T12:51:46Z)
• Particle Semi-Implicit Variational Inference [2.555222031881788]
  Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution.<n>Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities.<n>We propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions.
  arXiv  Detail & Related papers  (2024-06-30T10:21:41Z)
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
  We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT) We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity. In addition, we show that our approach enables us to explore more complex neural-based wave functions.
  arXiv  Detail & Related papers  (2023-03-01T10:38:10Z)
• Reweighted Interacting Langevin Diffusions: an Accelerated Sampling Methodfor Optimization [28.25662317591378]
  We propose a new technique to accelerate sampling methods for solving difficult optimization problems. Our method investigates the connection between posterior distribution sampling and optimization with Langevin dynamics.
  arXiv  Detail & Related papers  (2023-01-30T03:48:20Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• A Discrete Variational Derivation of Accelerated Methods in Optimization [68.8204255655161]
  We introduce variational which allow us to derive different methods for optimization. We derive two families of optimization methods in one-to-one correspondence. The preservation of symplecticity of autonomous systems occurs here solely on the fibers.
  arXiv  Detail & Related papers  (2021-06-04T20:21:53Z)
• Particle-based Energetic Variational Inference [4.079427359693159]
  We introduce a new variational inference (VI) framework, called energetic variational inference (EVI) We derive many existing Particle-based Variational Inference (ParVI) methods, including the popular Stein Variational Gradient Descent (SVGD) approach. We propose a new particle-based EVI scheme, which performs the particle-based approximation of the density first and then uses the approximated density in the variational procedure.
  arXiv  Detail & Related papers  (2020-04-14T12:14:08Z)
• Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs [71.26657499537366]
  We propose a simple literature-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method to train neural ODEs on classification, density estimation, and inference approximation tasks.
  arXiv  Detail & Related papers  (2020-03-11T13:15:57Z)

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.