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.
The paper shows how reducible complexes affect local indicability.
Vaisman's theorem extended to locally reducible Kähler spaces.
Optimal lower bounds for eigenvalues of Dirac-Witten operator on certain submanifolds.
In this paper, we get estimates on the higher eigenvalues of the Dirac operator on locally reducible Riemannian manifolds, in terms of the eigenvalues of the Laplace-Beltrami operator and the scalar curvature. These estimates are sharp, in the sense that, for the first eigenvalue, they reduce to the result of Alexandro…
The paper extends a variance gamma model to quadratic functions, reducing arbitrage and computational costs.
Killing tensors on reducible spaces are reducible, except for special cases.
We prove a lower estimate for the first eigenvalue of the Dirac operator on a compact locally reducible Riemannian spin manifold with positive scalar curvature. We determine also the universal covers of the manifolds on which the smallest possible eigenvalue is attained.
Continues work on derived manifolds and symplectic schemes, constructing virtual classes.
A reliable, accurate, and affordable positioning service is highly required in wireless networks. In this paper, the novel Message Passing Hybrid Localization (MPHL) algorithm is proposed to solve the problem of cooperative distributed localization using distance and direction estimates. This hybrid approach combines t…
Integrable symmetries of diffieties are studied, leading to local morphisms.
Reduced sh-Lie structures have been studied for the case when a Lie group acts on the fibers of a vector bundle while preserving the base space of the bundle. In this paper we investigate how one obtains a reduced sh-Lie structure using the ideas of symmetry reduction where the action of the Lie group is transversal to…
New method solves SLV models faster using Lie algebra.
The aim of the present paper is to provide a global presentation of the theory of special Finsler manifolds. We introduce and investigate globally (or intrinsically, free from local coordinates) many of the most important and most commonly used special Finsler manifolds: locally Minkowskian, Berwald, Landesberg, genera…
LSB is a new MCMC method for discrete spaces that reduces target evaluations.
We prove a holomorphic residue localization formula for odd holomorphic vector fields on compact complex supermanifolds whose fermionic and bosonic dimensions coincide. Under isolated non-degeneracy hypotheses on the reduced zero set, we give an explicit local residue formula.
We reduce the question of local nonsolvability of the Darboux equation, and hence of the isometric embedding problem for surfaces, to the local nonsolvability of a simple linear equation whose type is explicitly determined by the Gaussian curvature.
New method controls error in low-dimensional marginals of spatial models.
To accelerate the training of machine learning models, distributed stochastic gradient descent (SGD) and its variants have been widely adopted, which apply multiple workers in parallel to speed up training. Among them, Local SGD has gained much attention due to its lower communication cost. Nevertheless, when the data …
Localized diffusion models reduce training complexity by exploiting low-dimensional structure.
FedElasticNet reduces communication costs and handles client drift in FL.
Adaptive batch sizes improve local gradient methods in distributed training.
Optimal LDP mechanisms reduce data unfairness in classification.
A new method reduces the complexity of decentralized optimization.
Novel compression method preserves privacy while reducing communication costs.
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that …
A new method reduces communication costs in decentralized optimization.
The paper describes the structure of injective LOT-complexes and proves they are aspherical.
We study locally conformally Berwald metrics on closed manifolds which are not globally conformally Berwald. We prove that the characterization of such metrics is equivalent to characterizing incomplete, simply-connected, Riemannian manifolds with reducible holonomy group whose quotient by a group of homotheties is clo…
We consider several transformation groups of a locally conformally Kähler manifold and discuss their inter-relations. Among other results, we prove that all conformal vector fields on a compact Vaisman manifold which is neither locally conformally hyperkähler nor a diagonal Hopf manifold are Killing, holomorphic and th…
LocalNewton reduces communication in distributed learning.
A new method reduces communication costs in distributed learning.
Solves local minima problems on smooth manifolds.
We construct the most general reducible connection that satisfies the self-dual Yang-Mills equations on a simply connected, open subset of flat . We show how all such connections lie in the orbit of the flat connection on under the action of non-local symmetries of the self-dual Yang-Mills …
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client;…
Fixed point sets of certain group actions are contractible.
We derive identities for general flows of Riemannian metrics that may be regarded as local mean-value, monotonicity, or Lyapunov formulae. These generalize previous work of the first author for mean curvature flow and other nonlinear diffusions. Our results apply in particular to Ricci flow, where they yield a local mo…
One type of switch simplifies operations on lattice knots.
It is well-known that reduced smooth orbifolds and proper effective foliation Lie groupoids form equivalent categories. However, for certain recent lines of research, equivalence of categories is not sufficient. We propose a notion of maps between reduced smooth orbifolds and a definition of a category in terms of mark…
When scaling distributed training, the communication overhead is often the bottleneck. In this paper, we propose a novel SGD variant with reduced communication and adaptive learning rates. We prove the convergence of the proposed algorithm for smooth but non-convex problems. Empirical results show that the proposed alg…
The paper provides examples of keen weakly reducible bridge spheres for links in b-bridge position.
GradSkip reduces local training steps for better communication efficiency.
Control data constructed for smooth weak deformation retraction of stratified spaces.
Let M a 3-manifold with torus boundary which is a rational homology circle. We study deformations of reducible representations of p_1(M) into PSL_2(C) associated to a simple zero of the twisted Alexander polynomial. We also describe the local structure of the representation and character varieties.
Hill-climbing is a powerful baseline for NAS, even with reduced noise.
This (quasi-)survey addresses the quasi-isometry classification of locally compact groups, with an emphasis on amenable hyperbolic locally compact groups. This encompasses the problem of quasi-isometry classification of homogeneous negatively curved manifolds. A main conjecture provides a general description; an extend…
Novikov conjecture reduced to Lipschitz cohomology of groups.
We consider a distributed learning setup where a sparse signal is estimated over a network. Our main interest is to save communication resource for information exchange over the network and reduce processing time. Each node of the network uses a convex optimization based algorithm that provides a locally optimum soluti…
Distance metric learning is a successful way to enhance the performance of the nearest neighbor classifier. In most cases, however, the distribution of data does not obey a regular form and may change in different parts of the feature space. Regarding that, this paper proposes a novel local distance metric learning met…