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.
Study improves deep learning chest X-ray models by incorporating lateral views.
The MIMIC-CXR dataset is (to date) the largest released chest x-ray dataset consisting of 473,064 chest x-rays and 206,574 radiology reports collected from 63,478 patients. We present the results of training and evaluating a collection of deep convolutional neural networks on this dataset to recognize multiple common t…
Reprint of a 1989 paper including minor corrections of misprints. Added comments (11 pages) about later related papers in the literature concerning comparison of Gabriel-Zisman calculus of (right) fractions and the use of generalized morphims in the sense of Haefliger-Skandalis-Hilsum for inverting differentiable equiv…
The aim of this paper is to review and discuss in detail local aspects of principal bundles with groupoid structure. Many results, in particular from the second and third section, are already known to some extents, but, due to the lack of a ``unified'' point of view on the subject, I decided nonetheless to (re)define a…
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the highest layers but lateral connections from encoder to decoder relieve this pres…
Unified view on random walk and Weisfeiler-Leman kernels, improving accuracy.
Many problems in financial engineering involve the estimation of unknown conditional expectations across a time interval. Often Least Squares Monte Carlo techniques are used for the estimation. One method that can be combined with Least Squares Monte Carlo is the "Regress-Later" method. Unlike conventional methods wher…
The goal of this study is to explain and examine the statistical underpinnings of the Bollinger Band methodology. We start off by elucidating the rolling regression time series model and deriving its explicit relationship to Bollinger Bands. Next we illustrate the use of Bollinger Bands in pairs trading and prove the e…
Model-theoretic aspects of exotic smoothness were studied long ago uncovering unexpected relations to noncommutative spaces and quantum theory. Some of these relations were worked out in detail in later work. An important point in the argumentation was the forcing construction of Cohen but without a direct application …
The article explores how organisms and machines learn and recognize the world using Bayesian inference and thermodynamics.
A central problem in neuroscience is reconstructing neuronal circuits on the synapse level. Due to a wide range of scales in brain architecture such reconstruction requires imaging that is both high-resolution and high-throughput. Existing electron microscopy (EM) techniques possess required resolution in the lateral p…
The current leading computer vision models are typically feed forward neural models, in which the output of one computational block is passed to the next one sequentially. This is in sharp contrast to the organization of the primate visual cortex, in which feedback and lateral connections are abundant. In this work, we…
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
Convolutional neural network localizes OD and fovea in UWFoV-SLO images.
The thesis explores stability conditions and metrics in differential geometry.
Convolutional neural networks are commonly used to control the steering angle for autonomous cars. Most of the time, multiple long range cameras are used to generate lateral failure cases. In this paper we present a novel model to generate this data and label augmentation using only one short range fisheye camera. We p…
Human stablecoin transactions predict political risk in cryptocurrency markets.
Decision support tools that rely on supervised learning require large amounts of expert annotations. Using past radiological reports obtained from hospital archiving systems has many advantages as training data above manual single-class labels: they are expert annotations available in large quantities, covering a popul…
Hierarchical organization is a cornerstone of complexity and multifractality constitutes its central quantifying concept. For model uniform cascades the corresponding singularity spectra are symmetric while those extracted from empirical data are often asymmetric. Using the selected time series representing such divers…
Lagrange's map construction ideas influenced later mathematicians.
Measures difficulty of predictions to improve deep learning models.
In this work we consider the Taylor expansion of the exponential map of a submanifold immersed in R^n up to order three, in order to introduce the concepts of lateral and frontal deviation. We compute the directions of extreme lateral and frontal deviation for surfaces in R^3. Also we compute, by using the Taylor expan…
Unified view of Lion and Muon as Stochastic Frank-Wolfe methods.
Study on diagonal and separating coordinates for symmetric spaces of rank 1.
We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD algorithm weakly using the weak form of master equation for probability evolution. In the small ste…
The aim of these notes is to describe how to construct canonical bundles of moving frames and differential invariants for parametrized curves in Lagrangian Grassmannians, at least in the monotonic case. Such curves appear as Jacobi curves of sub-Riemannian extremals [1,2] . Originally this construction was done in [6,7…
HawkesLLM models text generation with temporal influence, improving semantic alignment under limited memory.
This paper will be splited into two papers and submited later.
Modified BP attribution methods often ignore later layers' information, leading to misleading explanations.
Unified framework for Bayesian and Frequentist statistics.
The paper studies boundedness of pseudo-differential operators on smooth manifolds.
Scarcity of labeled data is one of the most frequent problems faced in machine learning. This is particularly true in relation extraction in text mining, where large corpora of texts exists in many application domains, while labeling of text data requires an expert to invest much time to read the documents. Overall, st…
Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning and has been found to be employed in several intelligent species, including humans…
To better understand and improve the behavior of neural networks, a recent line of works bridged the connection between ordinary differential equations (ODEs) and deep neural networks (DNNs). The connections are made in two folds: (1) View DNN as ODE discretization; (2) View the training of DNN as solving an optimal co…
Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
This paper goes some way in explaining how to construct an integrable hierarchy of flows on the space of conformally immersed tori in n-space. These flows have first occured in mathematical physics -- the Novikov-Veselov and Davey-Stewartson hierarchies -- as kernel dimension preserving deformations of the Dirac operat…
A closer look at an example introduced by Livingston & Melvin and later studied by Miyazaki shows that a plumbing of two fibered ribbon knots (along their fiber surfaces) may be algebraically slice yet not ribbon.
Solved Dudeney's 100-year-old puzzle about triangle to square dissection.
We propose a DTCWT ScatterNet Convolutional Neural Network (DTSCNN) formed by replacing the first few layers of a CNN network with a parametric log based DTCWT ScatterNet. The ScatterNet extracts edge based invariant representations that are used by the later layers of the CNN to learn high-level features. This improve…
Study analyzes label smoothing in deep learning optimization.
This paper explores the capability of deep neural networks to capture key characteristics of vehicle dynamics, and their ability to perform coupled longitudinal and lateral control of a vehicle. To this extent, two different artificial neural networks are trained to compute vehicle controls corresponding to a reference…
We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection repres…
The Ricci flow is an evolution system on metrics. For a given metric as initial data, its local existence and uniqueness on compact manifolds was first established by Hamilton \cite{Ha1}. Later on, De Turck \cite{De} gave a simplified proof. In the later of 80's, Shi \cite{Sh1} generalized the local existence result to…
We announce some results towards the classification of partially hyperbolic diffeomorphisms on 3-manifolds, and outline the proofs in the case when the diffeomorphism is dynamically coherent. Detailed proofs are long and technical and will appear later.
The article studies factorization structures in geometry and their applications to cones and polytopes.
We give a shorter proof of the existence of nontrivial closed minimal hypersurfaces in closed smooth --dimensional Riemannian manifolds, a theorem proved first by Pitts for and extended later by Schoen and Simon to any .
This article was originally published in Topology 22 (1983). The present hyperTeXed redaction includes references to post-1983 results as Addenda, and corrects a few typographical errors. (See math.GT/0411115 for a more comprehensive overview of the subject as it appears 21 years later.)
Neural networks can overfit perfectly to noisy data and then grok near-optimal generalization.