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.
Spacematch matches office workers with suitable workspaces based on their preferences.
Shared workspace improves neural module coordination in deep learning.
We propose a novel neural network architecture, named the Global Workspace Network (GWN), which addresses the challenge of dynamic and unspecified uncertainties in multimodal data fusion. Our GWN is a model of attention across modalities and evolving through time, and is inspired by the well-established Global Workspac…
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying h…
NVIDIA cuDNN is a low-level library that provides GPU kernels frequently used in deep learning. Specifically, cuDNN implements several equivalent convolution algorithms, whose performance and memory footprint may vary considerably, depending on the layer dimensions. When an algorithm is automatically selected by cuDNN,…
Tripod spiders' energy control analyzed for Hooke and Coulomb potentials.
Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, and image segmentation. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, and Bayesian clas…
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue…
Proposes Learnergy, a Python framework for energy-based machine learning.
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL typically suffers from accumulating errors. Several recent studies have addressed thi…
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
New framework models epistemic uncertainty in GNNs using random sets.
JuliaConnectoR integrates Julia functions into R for deep learning.
In this paper we define and study flexible links and flexible isotopy in projective space. Flexible links are meant to capture the topological properties of real algebraic links. We classify all flexible links up to flexible isotopy using Ekholms interpretation of Viros encomplexed writhe.
The authors characterize flexibility in power and energy markets considering time, spatiality, resource, and risk.
TASO optimizes CNN models for memory-constrained devices.
New inequality for odd-degree flexible curves using surface doubling.
Automates detection of fast-ramped flexibility events for DSOs.
Flexible surfaces found in complex projective and product spaces.
Polyhedra called Siamese dipyramids are known to be non-flexible, however their physical models behave like physical models of flexible polyhedra. We discuss a simple mathematical method for explaining the model flexibility of the Siamese dipyramids.
TUV Austria proposes certification for ML applications to ensure reliability.
In this paper we study infinitesimal and finite flexibility for generic semidiscrete surfaces. We prove that generic 2-ribbon semidiscrete surfaces have one degree of infinitesimal and finite flexibility. In particular we write down a system of differential equations describing isometric deformations in the case of exi…
The recent popularity of deep neural networks (DNNs) has generated a lot of research interest in performing DNN-related computation efficiently. However, the primary focus is usually very narrow and limited to (i) inference -- i.e. how to efficiently execute already trained models and (ii) image classification networks…
In this paper we study geometric, algebraic, and computational aspects of flexibility and infinitesimal flexibility of Kokotsakis meshes. A Kokotsakis mesh is a mesh that consists of a face in the middle and a certain band of faces attached to the middle face by its perimeter. In particular any 3x3-mesh made of quadran…
We analyse perception and memory, using mathematical models for knowledge graphs and tensors, to gain insights into the corresponding functionalities of the human mind. Our discussion is based on the concept of propositional sentences consisting of \textit{subject-predicate-object} (SPO) triples for expressing elementa…
Weiss and, independently, Mazzeo and Montcouquiol recently proved that a 3--dimensional hyperbolic cone-manifold (possibly with vertices) with all cone angles less than is infinitesimally rigid. On the other hand, Casson provided 1998 an example of an infinitesimally flexible cone-manifold with some of the cone an…
Characterizes rigid and flexible hyperbolic cone metrics and billiards.
The paper defines flexible domains for minimal surfaces in Euclidean spaces and explores their properties.
Adma proposes a flexible loss function for neural networks.
Study shows non-existence of certain contact structures on odd-dimensional manifolds.
Flexible metrics found on a genus 2 surface.
We discuss several rigidity and flexibility phenomena in the context of Poisson geometry.
Flexible model for complex relationships using Bayesian nonparametrics.
Extends Hawkes process for flexible residual modeling in point processes.
Frengression models causal data flexibly and faithfully.
Establishes jet transversality for regular maps from flexible manifolds.
Flexible links have symplectic representatives in complex projective space.
New ADMM method for PARAFAC2 tensor decomposition with flexible regularization.
Flexible per-class regularization improves binary classifiers.
We show that surface groups are flexibly stable in permutations. This is the first non-trivial example of a non-amenable flexibly stable group. Our method is purely geometric and relies on an analysis of branched covers of hyperbolic surfaces. Along the way we establish a quantitative variant of the LERF property for s…
Shows flexible sheaves as fibrant objects for Gromov's h-principle.
Improved algorithm for optimal stopping problems reduces runtime.
We introduce and discuss notions of regularity and flexibility for Lagrangian manifolds with Legendrian boundary in Weinstein domains. There is a surprising abundance of flexible Lagrangians. In turn, this leads to new constructions of Legendrians submanifolds and Weinstein manifolds. For instance, many closed -mani…
New PAC-Bayesian framework for flexible meta-learning.
Combines MCTM and NF for flexible multivariate density regression with interpretable marginals.
TM-VI uses flexible transformation models to approximate complex posteriors in Bayesian models.
The present paper gives an example of a rigid spherical cone-manifold and that of a flexible one which are both Seifert fibred.