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 extends Weyl's law to CROSSes, showing sharpness and polynomial improvement.
This note provides an error bound for the Hartman-Watson integral's leading term.
The paper analyzes CycleGAN's error components for unpaired data generation.
The study analyzes implicit biases in neural networks using backward error analysis.
Improved generalization bounds for SGD in non-convex learning.
Estimates proper calibration errors and refinement terms in probabilistic predictions.
Paper analyzes LSA algorithm bias and error bounds with RR extrapolation.
The study sets lower bounds on MMSE for inferring sensitive features from noisy data.
In the present paper, a decomposition formula for the call price due to Alòs is transformed into a Taylor type formula containing an infinite series with stochastic terms. The new decomposition may be considered as an alternative to the decomposition of the call price found in a recent paper of Alòs, Gatheral and Radoi…
Recent works have derived non-asymptotic upper bounds for convergence of underdamped Langevin MCMC. We revisit these bound and consider introducing scaling terms in the underlying underdamped Langevin equation. In particular, we provide conditions under which an appropriate scaling allows to improve the error bounds in…
Efficient kernel method learns differential equations with fewer data.
End-to-end ASR error detection using audio-transcript entailment.
We develop a technique for deriving data-dependent error bounds for transductive learning algorithms based on transductive Rademacher complexity. Our technique is based on a novel general error bound for transduction in terms of transductive Rademacher complexity, together with a novel bounding technique for Rademacher…
New approach shapes error distribution in long-term forecasting.
In this paper, in following of the first part (which ADF tests using ACI evaluation) has conducted, Time Series (TSs) are analyzed using decomposition analysis. In fact, TSs are composed of four components including trend (long term behavior or progression of series), cyclic component (non-periodic fluctuation behavior…
The paper analyzes prediction error in nonstationary settings using weighted risk minimization.
Certain theoretical aspects of vector autoregression (VAR) as tools to model economic time series are revised, in particular their capacity to include both short term and long term information. The VAR model, in its error correction form, is derived and the permanent-transitory decomposition of factors proposed by Gonz…
In this paper we consider portmanteau tests for testing the adequacy of multiplicative seasonal autoregressive moving-average (SARMA) models under the assumption that the errors are uncorrelated but not necessarily independent.We relax the standard independence assumption on the error term in order to extend the range …
Cryptocurrency prices predicted using LSTM, SVM, and polynomial regression.
Study counts geodesics on hyperbolic 3-manifolds, proving prime theorems.
We study the linear ill-posed inverse problem with noisy data in the statistical learning setting. Approximate reconstructions from random noisy data are sought with general regularization schemes in Hilbert scale. We discuss the rates of convergence for the regularized solution under the prior assumptions and a certai…
Study optimizes solving fixed-point equations using subspace search.
New LT-O-learners improve HLTE estimation with low overlap.
LSTM Networks accurately forecast COVID-19 cases in Turkey with lower error than other methods.
TD learning reduces prediction error in Markov chain problems.
Study error bounds in evaluating distributional computational graphs.
Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated. A robust statistics view of GANs is considered to bound the error probability for various GAN implementations in terms of their performance. The bounds are further simplified using a Euclidean approximatio…
Multiplicative noise models are often used instead of additive noise models in cases in which the noise variance depends on the state. Furthermore, when Poisson distributions with relatively small counts are approximated with normal distributions, multiplicative noise approximations are straightforward to implement. Th…
Estimates surface count with prescribed foliations.
The lasso has been studied extensively as a tool for estimating the coefficient vector in the high-dimensional linear model; however, considerably less is known about estimating the error variance in this context. In this paper, we propose the natural lasso estimator for the error variance, which maximizes a penalized …
Study stability thresholds of big line bundles, proving bounds and generalizing results.
Estimates point counts in Teichmüller space for mapping class groups.
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
The accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about th…
Random forest training yields confidence intervals for generalization error.
OptiNet achieves near-minimax error rates with compression in Euclidean space.
We consider the minimum error entropy (MEE) criterion and an empirical risk minimization learning algorithm in a regression setting. A learning theory approach is presented for this MEE algorithm and explicit error bounds are provided in terms of the approximation ability and capacity of the involved hypothesis space w…
We provide a bound for the error committed when using a Fourier method to price European options when the underlying follows an exponential \levy dynamic. The price of the option is described by a partial integro-differential equation (PIDE). Applying a Fourier transformation to the PIDE yields an ordinary differential…
New method identifies root causes in presence of latent confounding.
New bounds tighten the generalization error of Gibbs algorithm.
For binary classification we establish learning rates up to the order of for support vector machines (SVMs) with hinge loss and Gaussian RBF kernels. These rates are in terms of two assumptions on the considered distributions: Tsybakov's noise assumption to establish a small estimation error, and a new geometr…
Derives EoM for DNNs to describe GD dynamics precisely.
Mutual information bounds generalization error in variational classifiers.
We design a new algorithm for the Euclidean -means problem that operates in the local model of differential privacy. Unlike in the non-private literature, differentially private algorithms for the -means objective incur both additive and multiplicative errors. Our algorithm significantly reduces the additive erro…
BSG learns dynamic network spillovers and uncertainty quantification.
Estimates the number of closed curves on surfaces with power-saving error terms.
Adversarial training achieves optimal test error for shallow networks.
We study convergence rates of variational posterior distributions for nonparametric and high-dimensional inference. We formulate general conditions on prior, likelihood, and variational class that characterize the convergence rates. Under similar "prior mass and testing" conditions considered in the literature, the rat…