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.
Automatic computation speeds up crosscap number calculation for alternating knots.
Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and generalizes the method of backwards propagation of errors used in machine learni…
Functional AD for Weil algebra computations.
agtboost speeds up gradient tree boosting with automatic complexity adjustment.
Super-efficient automatic differentiation outperforms analytic methods in min-min optimization.
Two of the most important areas in computational finance: Greeks and, respectively, calibration, are based on efficient and accurate computation of a large number of sensitivities. This paper gives an overview of adjoint and automatic differentiation (AD), also known as algorithmic differentiation, techniques to calcul…
A method makes particle filters differentiable without altering their forward pass.
We use AD to compute gradients for complex functionals in stochastic model calibration.
Melanoma is the deadliest form of skin cancer. Computer systems can assist in melanoma detection, but are not widespread in clinical practice. In 2016, an open challenge in classification of dermoscopic images of skin lesions was announced. A training set of 900 images with corresponding class labels and semi-automatic…
This paper deals with the computation of second or higher order greeks of financial securities. It combines two methods, Vibrato and automatic differentiation and compares with other methods. We show that this combined technique is faster than standard finite difference, more stable than automatic differentiation of se…
RAD estimates gradients with less memory, faster than small batch sizes.
CoLA automates efficient numerical linear algebra for complex matrix structures.
We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demo…
We propose a novel algorithm for efficiently computing a sparse directed adjacency matrix from a group of time series following a causal graph process. Our solution is scalable for both dense and sparse graphs and automatically selects the LASSO coefficient to obtain an appropriate number of edges in the adjacency matr…
Bayesian TNKMs automatically infer model complexity and feature relevance.
The theory of automatic groups is developed, including properties and practical algorithms.
Storchastic improves stochastic AD for complex models in RL and VI.
Geometric AD framework simplifies derivative computation in JAX.
Automatic differentiation is involved for long in applied mathematics as an alternative to finite difference to improve the accuracy of numerical computation of derivatives. Each time a numerical minimization is involved, automatic differentiation can be used. In between formal derivation and standard numerical schemes…
AD-HOC simplifies high-order derivative calculations in C++.
The exploitation of large-scale population data has the potential to improve healthcare by discovering and understanding patterns and trends within this data. To enable high throughput analysis of cardiac imaging data automatically, a pipeline should comprise quality monitoring of the input images, segmentation of the …
GShard enables scaling of large neural networks with automatic sharding and lightweight APIs.
A new method computes gradients without backpropagation.
This work integrates differentiation and integration in Physics-Informed Neural Networks.
AutoFIS automatically selects important feature interactions for CTR prediction models.
A new method for automatically aligning and clustering time series data.
The paper proposes a method to compute higher infinitesimals in numerical and symbolic analysis.
The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automati…
Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of…
In this work, we discuss the Automatic Adjoint Differentiation (AAD) for functions of the form , which often appear in the calibration of stochastic models. { We demonstrate that it allows a perfect SIMD\footnote{Single Input Multiple Data} parallelization and provide its relative co…
We prove a computable version of de Finetti's theorem on exchangeable sequences of real random variables. As a consequence, exchangeable stochastic processes expressed in probabilistic functional programming languages can be automatically rewritten as procedures that do not modify non-local state. Along the way, we pro…
pySigLib speeds up signature-based computations on CPUs and GPUs.
Develops a new flexible grid trading model using ANN and SSO.
Learn to automatically plug domain-specific modules into a common network.
NARD extends ARD for linear models, promoting sparsity and correlation structure.
Simplifies efficient estimation via automatic differentiation and probabilistic programming.
Python package for fast simulation-based inference.
Bayesian network structures are usually built using only the data and starting from an empty network or from a naive Bayes structure. Very often, in some domains, like medicine, a prior structure knowledge is already known. This structure can be automatically or manually refined in search for better performance models.…
Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic…
Proposes efficient, modular method for implicit differentiation.
Automatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architectu…
Systematic and multifactor risk models are revisited via methods which were already successfully developed in signal processing and in automatic control. The results, which bypass the usual criticisms on those risk modeling, are illustrated by several successful computer experiments.
AFR simplifies reducing reliance on spurious features, improving model performance.
HTE improves PINNs for high-dimensional, high-order PDEs by reducing computational cost and memory usage.
Automatic conflict detection has grown in relevance with the advent of body-worn technology, but existing metrics such as turn-taking and overlap are poor indicators of conflict in police-public interactions. Moreover, standard techniques to compute them fall short when applied to such diversified and noisy contexts. W…
Neural connectomics has begun producing massive amounts of data, necessitating new analysis methods to discover the biological and computational structure. It has long been assumed that discovering neuron types and their relation to microcircuitry is crucial to understanding neural function. Here we developed a nonpara…
ViViT efficiently computes curvature for deep networks without approximations.
Interactive applications incorporating high-data rate sensing and computer vision are becoming possible due to novel runtime systems and the use of parallel computation resources. To allow interactive use, such applications require careful tuning of multiple application parameters to meet required fidelity and latency …