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.
A new KM clustering algorithm reduces error and scales to large datasets.
Gaussian process regression helps approximate Bayesian inverse problems efficiently.
Bayesian method recovers causal structure in SEMs with equal error variances.
Paper assesses error estimates of Random Forests classification.
New bounds quantify estimation error in kernel-based system identification with unknown hyperparameters.
New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.
Improved estimator for least squares using random projections achieves smaller error.
Method detects errors in numerical data using regression models.
Bayesian method identifies causal DAG structure from non-Gaussian errors.
We develop coreset techniques for noisy clustering with provable guarantees.
Paper fine-tunes a simulation-driven estimator to reduce out-of-distribution errors.
In this paper we study the consistency of an empirical minimum error entropy (MEE) algorithm in a regression setting. We introduce two types of consistency. The error entropy consistency, which requires the error entropy of the learned function to approximate the minimum error entropy, is shown to be always true if the…
The Bellman error is a poor proxy for value function accuracy, even with all state-action pairs.
Two kernel Stein tests control decision errors in non-parametric model comparison.
Efficient algorithms identify true hypothesis from many options with minimal actions.
The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been…
New error bound for diffusion models without dimensionality constraints.
Study uses auxiliary data to estimate system dynamics, reducing noise error.
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 …
The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting. Its proof, however, contains an error in its bound on the effective dimensionality. In this note, we explain the mistake, provide a correct bound, and show that the main theorem remai…
In compressed sensing, in order to recover a sparse or nearly sparse vector from possibly noisy measurements, the most popular approach is -norm minimization. Upper bounds for the - norm of the error between the true and estimated vectors are given in [1] and reviewed in [2], while bounds for the $\ell_…
New proof shows how to identify DAGs with weakly increasing errors.
The problem of maximum-likelihood (ML) estimation of discrete tree-structured distributions is considered. Chow and Liu established that ML-estimation reduces to the construction of a maximum-weight spanning tree using the empirical mutual information quantities as the edge weights. Using the theory of large-deviations…
DFM models are analyzed for generating distributions with provable convergence.
In many signal detection and classification problems, we have knowledge of the distribution under each hypothesis, but not the prior probabilities. This paper is aimed at providing theory to quantify the performance of detection via estimating prior probabilities from either labeled or unlabeled training data. The erro…
The paper analyzes error bounds and KL properties for noisy matrix recovery problems.
Non-negative matrix factorization (NMF) is a knowledge discovery method that is used in many fields. Variational inference and Gibbs sampling methods for it are also wellknown. However, the variational approximation error has not been clarified yet, because NMF is not statistically regular and the prior distribution us…
Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the prop…
In regression settings where explanatory variables have very low correlations and there are relatively few effects, each of large magnitude, we expect the Lasso to find the important variables with few errors, if any. This paper shows that in a regime of linear sparsity---meaning that the fraction of variables with a n…
A procedure for unfolding the true distribution from experimental data is presented. Machine learning methods are applied for simultaneous identification of an apparatus function and solving of an inverse problem. A priori information about the true distribution from theory or previous experiments is used for Monte-Car…
Paper is withdrawn due to errors (superseded by math.AG/0604303). Formula 6.5 is false. Section 6 is false, and the main statement is true only for bundles with SU(2)-invariant.
Paper withdrawn due to errors (superseded by math.AG/0604303). Proposition 11.4 is false, Section 12 is false, and the main statement is true only for bundles with SU(2)-invariant.
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…
Paper proposes an algorithm to reduce hypothesis space for faster convergence in high-dimensional settings.
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account…
The paper analyzes the generalization of deep neural networks for metric and similarity learning.
Paper analyzes Gibbs and Langevin Monte Carlo for interpolation regime, showing generalization from low errors.
Using methods of statistical physics, we analyse the error of learning couplings in large Ising models from independent data (the inverse Ising problem). We concentrate on learning based on local cost functions, such as the pseudo-likelihood method for which the couplings are inferred independently for each spin. Assum…
New method improves model calibration efficiency and accuracy.
This work bounds classification error in machine learning for low Bayes error conditions.
New bounds show robust models can generalize well, contrary to prior theories.
This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators' to a distribution over the true error. The variance of this distribution can be…
Paper studies fairness postprocessing with imperfect attribute information.
Consider observing an undirected network that is `noisy' in the sense that there are Type I and Type II errors in the observation of edges. Such errors can arise, for example, in the context of inferring gene regulatory networks in genomics or functional connectivity networks in neuroscience. Given a single observed ne…
Paper proposes a cost-sensitive conformal training method with provably controllable learning bounds.
We consider the mixed regression problem with two components, under adversarial and stochastic noise. We give a convex optimization formulation that provably recovers the true solution, and provide upper bounds on the recovery errors for both arbitrary noise and stochastic noise settings. We also give matching minimax …
CD-RCA method identifies causal relationships in prediction errors without predefined graphs.