Implicit Riemannian Concave Potential Maps

• URL: http://arxiv.org/abs/2110.01288v1
• Date: Mon, 4 Oct 2021 09:53:20 GMT
• Title: Implicit Riemannian Concave Potential Maps
• Authors: Danilo J. Rezende, S\'ebastien Racani\`ere
• Abstract summary: This work combines ideas from implicit neural layers and optimal transport theory to propose a generalisation of existing work on exponential map flows. IRCPMs have some nice properties such as simplicity of incorporating symmetries and are less expensive than ODE-flows. We provide an initial theoretical analysis of its properties and layout sufficient conditions for stable optimisation.
• Score: 2.8137865669570297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We are interested in the challenging problem of modelling densities on Riemannian manifolds with a known symmetry group using normalising flows. This has many potential applications in physical sciences such as molecular dynamics and quantum simulations. In this work we combine ideas from implicit neural layers and optimal transport theory to propose a generalisation of existing work on exponential map flows, Implicit Riemannian Concave Potential Maps, IRCPMs. IRCPMs have some nice properties such as simplicity of incorporating symmetries and are less expensive than ODE-flows. We provide an initial theoretical analysis of its properties and layout sufficient conditions for stable optimisation. Finally, we illustrate the properties of IRCPMs with density estimation experiments on tori and spheres.

Related papers

• Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme [51.56484100374058]
  Low-dimensional structure in real-world data plays an important role in the success of generative models.<n>We prove convergence theory of numerical schemes for manifold-valued differential equations.
  arXiv  Detail & Related papers  (2026-03-04T01:29:35Z)
• Locally Purified Maximally Mixed States At Scale: Entanglement Pruning and Symmetries [0.0]
  Localized Purified Density Operators represent mixed quantum states at scale.<n>Given their non-uniqueness, their representational complexity is generally sub-optimal in practical computations.<n>We show how, by minimizing the resources required to represent key states of practical interest, the efficiency of tensor network algorithms can be substantially increased.
  arXiv  Detail & Related papers  (2025-09-19T21:38:29Z)
• Riemannian Variational Flow Matching for Material and Protein Design [37.328940532069424]
  In Euclidean space, predicting endpoints (VFM), velocities (FM), or noise (diffusion) are largely equivalent due to affines.<n>On curved manifold, this equivalence breaks down, and we hypothesize that endpoint prediction provides a stronger learning signal.<n>Building on this insight, we derive a variational flow matching objective.<n> Experiments on synthetic spherical and hyperbolic benchmarks, as well as real-world tasks in material and protein generation, demonstrate that RG-VFM more effectively captures manifold structure.
  arXiv  Detail & Related papers  (2025-02-18T16:02:10Z)
• Hamiltonian Lattice Gauge Theories: emergent properties from Tensor Network methods [0.0]
  This thesis develops advanced Network (TN) methods to address Hamiltonian Lattice Theories (LGTs) A novel dressed-site formalism is introduced, enabling efficient truncation of gauge fields. These advances open current and future development pathways toward optimized, efficient, and faster simulations on scales comparable to Monte Carlo state-of-the-art.
  arXiv  Detail & Related papers  (2025-01-19T17:09:57Z)
• Simulating the Hubbard Model with Equivariant Normalizing Flows [0.0]
  normalizing flows have been successfully applied to accurately learn the Boltzmann distribution. We present a proof-of-concept demonstration that normalizing flows can be used to learn the Boltzmann distribution for the Hubbard model.
  arXiv  Detail & Related papers  (2025-01-13T14:40:42Z)
• Truncated Gaussian basis approach for simulating many-body dynamics [0.0]
  The approach constructs an effective Hamiltonian within a reduced subspace, spanned by fermionic Gaussian states, and diagonalizes it to obtain approximate eigenstates and eigenenergies. Symmetries can be exploited to perform parallel computation, enabling to simulate systems with much larger sizes. For quench dynamics we observe that time-evolving wave functions in the truncated subspace facilitates the simulation of long-time dynamics.
  arXiv  Detail & Related papers  (2024-10-05T15:47:01Z)
• Analysis on Riemann Hypothesis with Cross Entropy Optimization and Reasoning [2.1046873879077794]
  The framework is composed of three key components. Probability modeling with cross entropy optimization and reasoning. The application of the law of large numbers and mathematical inductions.
  arXiv  Detail & Related papers  (2024-09-29T21:25:58Z)
• Quantum-electrodynamical density-functional theory for the Dicke Hamiltonian [0.0]
  A detailed analysis of density-functional theory for quantum-electrodynamical model systems is provided. In particular, the quantum Rabi model, the Dicke model, and the latter to multiple modes are considered.
  arXiv  Detail & Related papers  (2024-09-18T12:53:36Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Adaptive Log-Euclidean Metrics for SPD Matrix Learning [73.12655932115881]
  We propose Adaptive Log-Euclidean Metrics (ALEMs), which extend the widely used Log-Euclidean Metric (LEM) The experimental and theoretical results demonstrate the merit of the proposed metrics in improving the performance of SPD neural networks.
  arXiv  Detail & Related papers  (2023-03-26T18:31:52Z)
• Efficient simulation of Gottesman-Kitaev-Preskill states with Gaussian circuits [68.8204255655161]
  We study the classical simulatability of Gottesman-Kitaev-Preskill (GKP) states in combination with arbitrary displacements, a large set of symplectic operations and homodyne measurements. For these types of circuits, neither continuous-variable theorems based on the non-negativity of quasi-probability distributions nor discrete-variable theorems can be employed to assess the simulatability.
  arXiv  Detail & Related papers  (2022-03-21T17:57:02Z)
• Riemannian Convex Potential Maps [28.39224890275125]
  We propose and study a class of flows that uses convex potentials from Riemannian optimal transport. We demonstrate that these flows can model standard distributions on spheres, and tori, on synthetic and geological data.
  arXiv  Detail & Related papers  (2021-06-18T17:59:06Z)
• A Unifying and Canonical Description of Measure-Preserving Diffusions [60.59592461429012]
  A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. We develop a geometric theory that improves and generalises this construction to any manifold.
  arXiv  Detail & Related papers  (2021-05-06T17:36:55Z)
• Bayesian Quadrature on Riemannian Data Manifolds [79.71142807798284]
  A principled way to model nonlinear geometric structure inherent in data is provided. However, these operations are typically computationally demanding. In particular, we focus on Bayesian quadrature (BQ) to numerically compute integrals over normal laws. We show that by leveraging both prior knowledge and an active exploration scheme, BQ significantly reduces the number of required evaluations.
  arXiv  Detail & Related papers  (2021-02-12T17:38:04Z)

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.