Research
On-device research index

arXiv research

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.

169,291 papers · 148 categories

Trend · papers per month

72145217289 · Jun 202019922001200920182026
48 results for least-squares error

Study improves least squares estimation for heavy-tailed errors.

problem Improving least squares estimation under heteroscedastic and heavy-tailed errors.
method Analyzes the rate of convergence of least squares estimator under bounded conditional variance and finitely many moments of errors.
result Upper bounds on rates of convergence of LSE for heavy-tailed errors are found.

The paper examines prediction and estimation risks of ridgeless least squares under general error assumptions.

problem Prediction and estimation risks of ridgeless least squares under realistic error structures.
method Analysis of prediction and estimation risks under general regression error assumptions, including clustered or serial dependence.
result The benefits of overparameterization extend to time series, panel, and grouped data.

Efficiently estimates private least squares with linear error growth.

problem Private estimation of ordinary least squares with bounded residuals and leverage.
method Scaled noise added to a stable nonprivate estimator of the regression vector.
result Near-optimal accuracy guarantee with linear error growth in dimension.

Distributed learning with least squares regularization achieves good performance without eigenfunction assumptions.

problem Efficiently learning from large datasets distributed across multiple machines.
method Divide-and-conquer approach, least squares regularization, RKHS, error bounds in expectation.
result The global estimator is a good approximation to the full data estimator, with sharp error bounds.

Improved estimator for least squares using random projections achieves smaller error.

problem Improving the accuracy of least squares solutions for large-scale problems.
method James-Stein estimator applied to Gaussian sketching of least squares problems.
result Upper and lower bounds match when SNR is small and data matrix is well-conditioned.

Randomized matrix compression techniques, such as the Johnson-Lindenstrauss transform, have emerged as an effective and practical way for solving large-scale problems efficiently. With a focus on computational efficiency, however, forsaking solutions quality and accuracy becomes the trade-off. In this paper, we investi…

2015-10-16abs ↗pdf ↗

A fast sketching algorithm solves regularized least squares problems efficiently.

problem Solving large-scale optimization problems with convex or nonconvex regularization.
method Sketching for Regularized Optimization (SRO) algorithm that generates a sketch of the original data matrix and solves the sketched problem.
result General theoretical results for the approximation error between the original and sketched problems, including minimax rates for sparse signal estimation.

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…

2012-08-03abs ↗pdf ↗

Efficient method for high-dimensional American option pricing and hedging.

problem High-dimensional American option pricing and hedging.
method Gradient-enhanced sparse Hermite polynomial expansions combined with least squares Monte Carlo.
result Outperforms state-of-the-art methods in high dimensions with comparable computational cost.

A new algorithm solves nonnegative least squares faster with nonnegative data.

problem Nonnegative least squares problems with nonnegative data.
method Primal-dual perspective accelerated algorithm with adaptive restart.
result Oracle complexity independent of matrix constants, solvable to multiplicative error.

This work refutes the conventional wisdom and shows acceleration can be made robust for least squares regression.

problem The challenge of using fast gradient methods for stochastic optimization due to instability and error accumulation.
method Introduced an accelerated stochastic gradient method for least squares regression.
result Proves accelerated stochastic gradient descent achieves minimax optimal statistical risk faster than SGD.

This book introduces linear models and their theories rigorously.

problem Understanding linear models and their theories.
method Explains linear models from three perspectives, introduces maximum likelihood estimation, and proves least squares is the best unbiased linear model.
result Least squares is the best unbiased linear model in terms of mean squared error.

Study of regularized least squares in RKKS with indefinite kernels.

problem Asymptotic properties of regularized least squares with indefinite kernels in RKKS.
method Introducing a bounded hyper-sphere constraint, theoretical demonstration of globally optimal solution, modified error decomposition techniques, matrix perturbation theory.
result Derivation of learning rates in RKKS, same as RKHS under certain conditions.

Study shows how mini-batch GD with random reshuffling affects least squares regression dynamics.

problem Analyzing the error dynamics of mini-batch GD with random reshuffling for least squares regression.
method Represented training and generalization errors through a sample cross-covariance matrix Z, compared with sample covariance matrix of original features X, and used linear scaling rule for analysis.
result Mini-batch GD with random reshuffling exhibits subtle step-size dependence not detectable by gradient flow analysis, converging to a limit dependent on the step size.

Study shows overparameterization helps in generalizing from smooth interpolants.

problem Understanding generalization in overparameterized linear models.
method Analysis of random Fourier series model with weighted trigonometric interpolation.
result Weighted trigonometric interpolation leads to lower generalization error in overparameterized scenarios.

We study the total least squares (TLS) problem that generalizes least squares regression by allowing measurement errors in both dependent and independent variables. TLS is widely used in applied fields including computer vision, system identification and econometrics. The special case when all dependent and independent…

2014-06-01abs ↗pdf ↗

Improved SGD for non-strongly-convex regression with faster convergence.

problem Non-strongly-convex least squares regression problems.
method Modified accelerated gradient descent.
result Achieves optimal prediction error rates of O(d/t)O(d/t) and forgets initial conditions faster to O(d/t2)O(d/t^2).

Derives optimal dynamic trading strategies under Gaussian assumptions.

problem Understanding and optimizing dynamic trading strategies in finance.
method Assumes Gaussian returns and dynamic weights, derives closed-form expressions for strategy returns moments.
result Positive skewness and excess kurtosis are essential for positive Sharpe dynamic strategies.

In this paper, we study a fast approximation method for {\it large-scale high-dimensional} sparse least-squares regression problem by exploiting the Johnson-Lindenstrauss (JL) transforms, which embed a set of high-dimensional vectors into a low-dimensional space. In particular, we propose to apply the JL transforms to …

2015-07-18abs ↗pdf ↗

Least Squares Estimators are suboptimal for 5D convex functions.

problem Suboptimality of Least Squares Estimators in estimating multidimensional convex functions.
method Analysis of natural subclasses of convex functions in random and fixed design settings.
result Risk of LSE is n2/dn^{-2/d} while minimax risk is n4/(d+4)n^{-4/(d+4)} for d5d \geq 5.

The paper identifies saddlepoints in unsupervised auto-encoding neural nets.

problem The risk landscape of unsupervised least squares in auto-encoding neural nets.
method Established an equivalence between unsupervised least squares and principal manifolds, discussed regularization strategies for auto-encoders.
result All non-trivial critical points in auto-encoding are saddlepoints, which are degenerate in overcomplete auto-encoding.

We introduce a novel semi-supervised version of the least squares classifier. This implicitly constrained least squares (ICLS) classifier minimizes the squared loss on the labeled data among the set of parameters implied by all possible labelings of the unlabeled data. Unlike other discriminative semi-supervised method…

2015-07-24abs ↗pdf ↗

We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as…

2009-02-25abs ↗pdf ↗

The OLS estimator optimally identifies stable linear systems with a finite number of samples.

problem Identifying stable linear systems with a finite number of samples.
method Finite-time analysis of the Ordinary Least Squares (OLS) estimator for stable linear systems.
result The OLS estimator achieves optimal sample complexity for stable systems, matching existing lower bounds up to universal factors.

The paper proposes a least squares method for binary compressive sampling with low intrinsic dimension signals.

problem Recovering signals from binary measurements with noise and sign flips.
method Least squares decoder for signals with low generative intrinsic dimension.
result The least squares decoder achieves a sharp estimation error of O(klog(Ln)m)O(\sqrt{\frac{k\log (Ln)}{m}}) under certain conditions.

New algorithm improves regression error bounds and accelerates performance for low noise.

problem Nonparametric least square regression in RKHS with optimal error bounds.
method Kernel Truncated Randomized Ridge Regression (KTRRR) with optimal generalization error bounds.
result Faster finite-time and asymptotic rates on low noise problems.

Bayesian optimization selects wavelengths for sugar content estimation in NIR spectroscopy.

problem Improving prediction accuracy and interpretability of spectral data for sugar content estimation.
method Formulated as a binary black-box optimization problem, proposed method uses Bayesian optimization with a sparse quadratic surrogate model and Thompson sampling.
result Improves prediction accuracy of partial least squares regression and yields more consistent wavelength regions.

New algorithm reduces error in regression problems.

problem Minimizing composite objective functions with quadratic and convex components.
method Stochastic dual averaging with constant step-size, proving convergence rate O(1/n).
result Extends least-squares regression to various convex regularizers and geometries.

Study on learning properties of scale-dependent kernels controlling stability and error.

problem Understanding the learning properties of scale-dependent kernels in nonparametric ridge-less least squares.
method Combines probabilistic results with interpolation theory to analyze stability and error.
result Different regimes of learning error depending on sample size and data dimension.

We learn linear models from nonlinear systems using multiple trajectories and regularization.

problem Identifying linear models from data when the underlying dynamics are nonlinear.
method Multiple trajectories data acquisition followed by regularized least squares.
result Learn linearized dynamics with arbitrarily small error given enough samples.

A new framework for efficient large-scale learning using sketching of moments.

problem Efficiently learning from large datasets with limited computational resources.
method Compressing the training data into a low-dimensional sketch and solving a nonlinear least squares problem.
result Sufficient sketch sizes to control the generalization error of the procedure.

The paper tackles robust reinforcement learning with performance guarantees.

problem Finding a robust policy for RMDP with state space uncertainties.
method Proposes RLSPI algorithm for learning optimal robust policy with performance bounds.
result Demonstrates the performance of RLSPI on standard benchmark problems.

New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.

problem Learning value and advantage functions for continuous-time Markov processes without structural assumptions.
method Proposes Sobolev-prox fitted qq-learning algorithm based on Hilbert-space positive definiteness and boundedness properties of Bellman operators.
result Identifies ellipticity as a key structural property enabling reinforcement learning for Markov diffusions.

The paper shows how sketching data can simplify regression inference even when errors are heteroskedastic.

problem Performing robust inference with heteroskedastic errors using sketched data.
method Using random projections to sketch data, the paper shows that sketched estimates behave as if errors are homoskedastic.
result Estimation by random sampling does not have the same property, and sketched estimates are asymptotically normal with homoskedastic variance.

Study identifies and analyzes three types of errors in learning Fourier operators.

problem Statistical, discretization, and truncation errors in learning Fourier operators.
method Analysis of a Discrete Fourier Transform (DFT) based least squares estimator.
result Established upper and lower bounds on statistical, discretization, and truncation errors.

New algorithm estimates partially-observed linear systems with better rates than previous methods.

problem Estimating parameters of partially-observed linear systems with long-term dependencies and semi-parametric noise.
method Prefiltered least squares estimator with semi-parametric noise model.
result First algorithm provably estimates parameters of partially-observed linear systems with rates not dependent on dependency decay rate.

Study identifies and validates a method for system identification of Markov jump linear systems.

problem System identification for autonomous Markov jump linear systems with complete state observations.
method Proposes switched least squares method for identification and derives rates of convergence.
result Data-independent rate of convergence is O(log(T)/T)\mathcal{O}\big(\sqrt{\log(T)/T} \big), showing strong consistency.