Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Jun 199319922001200920172026
48 results for symplectic neural networks

Characterizes group-equivariant neural networks for three groups.

problem Understanding equivariant neural networks for orthogonal, special orthogonal, and symplectic groups.
method Characterized all possible group-equivariant neural networks for three groups.
result Found spanning sets of matrices for learnable, linear equivariant layer functions.

SSINNs learn Hamiltonian systems from data with interpretable, low-memory models.

problem Learning Hamiltonian dynamical systems from data efficiently and accurately.
method Combines fourth-order symplectic integration with sparse regression for a learned Hamiltonian.
result Outperforms state-of-the-art techniques in system prediction and energy conservation.

An algorithm for efficient computation of equivariant neural network layers.

problem Efficiently computing with Brauer's group equivariant neural network layers.
method Category theoretic constructions and Kronecker product matrices.
result Significant reduction in computational cost compared to naive implementation.

Novel method combines physics priors for energy-conserving dynamics.

problem Learning long-term dynamics of complex physical systems from noisy data.
method Variational Integrator Graph Networks integrating energy constraint, high-order symplectic integrators, and graph neural networks.
result Improves predictive performance across single and many-body problems.

New algorithm speeds up group equivariant neural networks computations.

problem Challenging computations in group equivariant neural networks.
method Diagrammatic framework based on category theory for matrix multiplication.
result Exponential improvement in time complexity for matrix multiplication.

New Adam optimizer generalized for manifold training of neural networks.

problem Lack of clear physical intuition and difficulty in generalizing Adam optimizer to manifolds.
method Leverages the global tangent space representation of manifolds to perform Adam optimizer steps.
result Significant speed-ups in transformer training with orthogonality constraints.

Hamiltonian RNN controls hidden states gradient for long-term dependencies.

problem Challenges in learning long-term dependencies in RNNs.
method Symplectic discretization of Hamiltonian system to control gradient.
result Hamiltonian RNN outperforms other RNNs without hyperparameter optimization.

The paper develops spectral networks in symplectic topology and their relation to Lagrangian fillings.

problem Understanding spectral networks in symplectic topology and their role in Lagrangian fillings.
method Analytic results on adiabatic degeneration of Floer trajectories and explicit computation of continuation strips.
result Established equivalence between Family Floer functor and non-abelianization functor for Lagrangian fillings with spectral networks.

SympNets identify Hamiltonian systems from data using linear, activation, and gradient modules.

problem Identifying Hamiltonian systems from data.
method Composition of linear, activation, and gradient modules; universal approximation theorems.
result SympNets can approximate arbitrary symplectic maps and generalize well to various Hamiltonian systems.

We consider the problem of sampling from posterior distributions for Bayesian models where some parameters are restricted to be orthogonal matrices. Such matrices are sometimes used in neural networks models for reasons of regularization and stabilization of training procedures, and also can parameterize matrices of bo…

2019-01-23abs ↗pdf ↗

SGNs use Hamiltonian mechanics for invertible deep generative modeling.

problem Efficient and exact likelihood evaluation for deep generative models.
method Symplectic structure in latent space, Hamiltonian dynamics for data generation.
result Exact likelihood evaluation without Jacobian calculations.

We provide a new topological interpretation of the symplectic properties of gluing equations for triangulations of hyperbolic 3-manifolds, first discovered by Neumann and Zagier. We also extend the symplectic properties to more general gluings of PGL(2,C) flat connections on the boundaries of 3-manifolds with topologic…

2014-03-20abs ↗pdf ↗

New approach relaxes inductive biases of physics-inspired NNs for better performance.

problem Challenges in applying physics-inspired NNs to real-world systems.
method Examined and relaxed inductive biases of Hamiltonian NNs, improving performance on non-conservative systems.
result Improved performance on practical, non-conservative systems by relaxing inductive biases.

A symplectic manifold (M,ω)(M,ω) is called {\em (symplectically) uniruled} if there is a nonzero genus zero GW invariant involving a point constraint. We prove that symplectic uniruledness is invariant under symplectic blow-up and blow-down. This theorem follows from a general Relative/Absolute correspondence for a symple…

2006-11-20abs ↗pdf ↗

Study on symplectic Dirac operators on foliations, estimating eigenvalues.

problem Estimating eigenvalues of transversely symplectic Dirac operators.
method Analysis of transversely symplectic structures and use of Weitzenbock formula.
result Estimation of lower bounds for eigenvalues of transversely symplectic Dirac operators.

We study topological properties of log-symplectic structures and produce examples of compact manifolds with such structures. Notably we show that several symplectic manifolds do not admit log-symplectic structures and several log-symplectic manifolds do not admit symplectic structures, for example #m CP^2 # n bar(CP^2)…

2013-03-26abs ↗pdf ↗

We describe the structure of the Lie groups endowed with a left-invariant symplectic form, called symplectic Lie groups, in terms of semi-direct products of Lie groups, symplectic reduction and principal bundles with affine fiber. This description is particularly nice if the group is Hamiltonian, that is, if the left c…

2009-07-01abs ↗pdf ↗

We consider aspherical manifolds with torsion-free virtually polycyclic fundamental groups, constructed by Baues. We prove that if those manifolds are cohomologically symplectic then they are symplectic. As a corollary we show that cohomologically symplectic solvmanifolds are symplectic.

2010-05-07abs ↗pdf ↗

Log-symplectic structures are Poisson structures that are determined by a symplectic form with logarithmic singularities. We construct moduli spaces of curves with values in a log-symplectic manifold. Among the applications, we classify symplectically ruled log-symplectic 44 manifolds (both orientable and non-orientab…

2017-11-29abs ↗pdf ↗

Symplectic fillings of prequantization bundles are shown to be disk bundles under certain conditions.

problem Characterizing symplectic fillings of prequantization bundles with finite capacities.
method Analysis of symplectic capacities and diffeomorphisms.
result Symplectic fillings of prequantization bundles are diffeomorphic to disk bundles under finite capacity conditions.

Study on symplectic semi-characteristic using cohomology and vector fields.

problem Defining and calculating the symplectic semi-characteristic of symplectic manifolds.
method Defined using even-degree primitive cohomology and proved a counting formula using vector fields.
result Established a counting formula for symplectic semi-characteristic and derived vanishing properties.

A symplectic form is called hyperbolic if its pull-back to the universal cover is a differential of a bounded one-form. The present paper is concerned with the properties and constructions of manifolds admitting hyperbolic symplectic forms. The main results are: * If a symplectic form represents a bounded cohomology cl…

2007-11-24abs ↗pdf ↗

New models for symplectic structures on classifying stacks.

problem Building models for symplectic structures on classifying stacks.
method Introducing mm-shifted symplectic Lie nn-groupoids and constructing explicit symplectic Morita equivalences.
result Explicit symplectic Morita equivalences between models of the 2-shifted symplectic structure on classifying stacks.

We introduce a method to resolve a symplectic orbifold into a smooth symplectic manifold. Then we study how the formality and the Lefschetz property of the symplectic resolution are compared with that of the symplectic orbifold. We also study the formality of the symplectic blow-up of a symplectic orbifold along symple…

2007-10-03abs ↗pdf ↗

Conditions are given under which an infinitesimal automorphism of a torsion-free connection preserving a symplectic form is necessarily a symplectic vector field. An example is given of a compact symplectic manifold admitting a flat symplectic connection and an infinitesimal automorphism that is not symplectic.

2015-11-30abs ↗pdf ↗

We study the local symplectic algebra of curves. We use the method of algebraic restrictions to classify symplectic W8W_8 and W9W_9 singularities. We use discrete symplectic invariants to distinguish symplectic singularities of the curves. We also give the geometric description of symplectic classes.

2012-02-06abs ↗pdf ↗

Fintushel and Stern defined the rational blow-down construction [FS] for smooth 4-manifolds, where a linear plumbing configuration of spheres CnC_n is replaced with a rational homology ball BnB_n, n2n \geq 2. Subsequently, Symington [Sy] defined this procedure in the symplectic category, where a symplectic CnC_n (given…

2013-03-11abs ↗pdf ↗

In this paper, we introduce the notion of a pre-symplectic algebroid, and show that there is a one-to-one correspondence between pre-symplectic algebroids and symplectic Lie algebroids. This result is the geometric generalization of the relation between left-symmetric algebras and symplectic (Frobenius) Lie algebras. A…

2016-04-01abs ↗pdf ↗

In [11], I. M. Gelfand, V. Retakh, and M. Shubin defined the symplectic sectional curvature of a torsion-free connection preserving a symplectic form. The present article defines the corresponding notion of constant symplectic sectional curvature and characterizes this notion in terms of the curvature tensor of the sym…

2016-10-19abs ↗pdf ↗