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.
Local SGD outperforms minibatch SGD for quadratic objectives.
This paper presents a simple but effective density-based outlier detection approach with the local kernel density estimation (KDE). A Relative Density-based Outlier Score (RDOS) is introduced to measure the local outlierness of objects, in which the density distribution at the location of an object is estimated with a …
Improves multi-objective learning by adapting to local subintervals.
Local-HDP learns independent topics for each 3D object category in real-time.
In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries …
A new algorithm optimizes local objectives in federated learning with heterogeneous clients.
Local surrogate explainers vary in objectives, leading to incomparable explanations.
Proposes a method for weakly-supervised object localization to improve few-shot learning.
The study explores how different Grothendieck topologies and functors between categories preserve locality.
Nonlinear embedding manifold learning methods provide invaluable visual insights into the structure of high-dimensional data. However, due to a complicated nonconvex objective function, these methods can easily get stuck in local minima and their embedding quality can be poor. We propose a natural extension to several …
3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to captu…
This paper tackles objective inconsistency in federated optimization with heterogeneous clients.
LRSAO uses RL to dynamically select and unlearn auxiliary objectives for EA optimization.
Improved Local SGD convergence for general convex objectives with bounded second-order heterogeneity.
Image segmentation is widely used in a variety of computer vision tasks, such as object localization and recognition, boundary detection, and medical imaging. This thesis proposes deep learning architectures to improve automatic object localization and boundary delineation for salient object segmentation in natural ima…
Novel CE-method variants reduce local minima convergence with fewer function evaluations.
We study locally compact contractive local groups, that is, locally compact local groups with a contractive pseudo-automorphism. We prove that if such an object is locally connected, then it is locally isomorphic to a Lie group. We also prove a related structure theorem for locally compact contractive local groups whic…
Robots detect and recognize objects in real-time for better manipulation.
Minibatch SGD outperforms Local SGD in heterogeneous distributed learning.
AGGLIO optimizes non-convex functions with local convexity guarantees.
The object of the present paper is to study the locally - semisymmetric Kenmotsu manifolds along with the characterization of such notion.
In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to estimate the probability of each predicted object in a given region and the confi…
Paper explores supervised learning methods to approximate ideal observer for joint signal detection and localization.
Local network community detection is the task of finding a single community of nodes concentrated around few given seed nodes in a localized way. Conductance is a popular objective function used in many algorithms for local community detection. This paper studies a continuous relaxation of conductance. We show that con…
LSB is a new MCMC method for discrete spaces that reduces target evaluations.
New method makes CP intervals locally adaptive using trainable transformations.
LoCo learns local representations without end-to-end synchronization, improving performance on complex tasks.
Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.
3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…
Cactus doodles are geometric objects derived from cactus groups.
Local mass perspective on Bayesian inference
We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their locally trained model by communicating with other agents that have similar object…
We prove the local convergence to minima and estimates on the rate of convergence for the stochastic gradient descent method in the case of not necessarily globally convex nor contracting objective functions. In particular, the results are applicable to simple objective functions arising in machine learning.
This work addresses local fairness in machine learning models.
Langevin dynamics (LD) has been proven to be a powerful technique for optimizing a non-convex objective as an efficient algorithm to find local minima while eventually visiting a global minimum on longer time-scales. LD is based on the first-order Langevin diffusion which is reversible in time. We study two variants th…
Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy achieved by top weakly supervised algorithms is still significantly lower than …
Novel method for high-dimensional BO using CMA to define local regions.
SVH-PSL uses Stein Variational Gradient Descent and Hypernetworks to improve Pareto set learning for expensive MOO.
Delta-AI speeds up inference in sparse PGMs by local credit assignment.
We present a distributed proximal-gradient method for optimizing the average of convex functions, each of which is the private local objective of an agent in a network with time-varying topology. The local objectives have distinct differentiable components, but they share a common nondifferentiable component, which has…
Optimizers find approximate global minima in non-convex problems.
In the present paper, we consider local moves on classical and welded diagrams: (self-)crossing change, (self-)virtualization, virtual conjugation, Delta, fused, band-pass and welded band-pass moves. Interrelationship between these moves is discussed and, for each of these move, we provide an algebraic classification. …
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
A Jet groupoid R_q over a manifold X is a special Lie groupoid consisting of q-jets of local diffeomorphisms from X to X. As a subbundle of the q-th order jet bundle of the trivial bundle X times X, a jet groupoid can be considered as a nonlinear system of partial differential equations (PDE). This leads to the concept…
New computational methods improve clustering of objects.
Paper presents a WiFi-based indoor sensor localization technique.
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
In this paper we introduce the notion of deformation cohomology for singular foliations and related objects (namely integrable differential forms and Nambu structures), and study it in the local case, i.e., in the neighborhood of a point.