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.

169,341 papers · 148 categories

Trend · papers per month

86172258344 · Jun 202019922001200920182026
48 results for piecewise-linear approximation

Piecewise-linear approximation improves feature selection in logit models.

problem Improving feature subset selection in sequential logit models.
method Applied piecewise-linear approximation to logistic loss function to frame feature selection as a mixed integer linear optimization problem.
result Piecewise-linear approximation found a better subset of features than quadratic approximation.

The paper approximates smooth isotropic surfaces with piecewise linear ones.

problem Approximating smooth isotropic surfaces with piecewise linear ones.
method Using analogies with infinite dimensional moment map geometry, the authors prove the approximation of smooth isotropic immersions by piecewise linear ones.
result Smooth isotropic immersions can be approximated by piecewise linear isotropic maps.

Efficiently finds sparse solutions to max-plus equations for convex regression.

problem Finding sparse solutions to max-plus equations for convex multivariate regression.
method Polynomial-time algorithm for sparse approximate solutions.
result Optimal piecewise-linear fitting with minimum number of regions.

A hybrid model combines piecewise linear and neural components for interpretable predictions.

problem Post-hoc interpretable methods lead to contradictory explanations and lower prediction accuracy.
method Hybrid model with piecewise linear and neural components.
result The model achieves good interpretability and state-of-the-art accuracy.

Tropical geometry and weighted lattices improve curve and surface fitting.

problem Fitting max-\star tropical curves and surfaces to data.
method Max-\star algebra, weighted lattices, morphological adjunctions.
result Optimal piecewise-linear regression for max-\star curves and surfaces.

Proposes new models to solve portfolio selection with cardinality constraints using factor models.

problem Solving portfolio selection with cardinality constraints using factor models.
method Developed 0-1 linear models and a minimum edge-weighted clique problem to solve the cardinality constrained portfolio problem.
result Piecewise linear approximation reduces computation time for solving the quadratic problem.

Deep networks with ReLU outperform piecewise linear spline methods in function approximation.

problem Comparing expressive power of deep neural networks with ReLU activation to piecewise linear spline methods.
method Comparison of function approximation capabilities between deep neural networks with ReLU activation and piecewise linear spline methods.
result Deep neural networks with ReLU activation can approximate functions better or only slightly worse than piecewise linear spline methods.

Given a piecewise linear (PL) function pp defined on an open subset of Rn\R^n, one may construct by elementary means a unique polyhedron with multiplicities $\D(p)$ in the cotangent bundle Rn×Rn\R^n\times \R^{n*} representing the graph of the differential of pp. Restricting to dimension 2, we show that any smooth functi…

2013-05-09abs ↗pdf ↗

The paper develops a method to approximate arbitrary Bregman divergences from supervision.

problem Approximating an arbitrary Bregman divergence from supervision.
method Develops a formulation and algorithm for learning arbitrary Bregman divergences by approximating their convex generating function via a piecewise linear function.
result The method achieves a generalization error of Op(m1/2)O_p(m^{-1/2}) for metric learning, matching known bounds.

The paper tackles prescribing discrete Gaussian curvature on polyhedral surfaces.

problem Prescribing discrete Gaussian curvature on polyhedral surfaces.
method Discrete conformal theory and variational principles with constraints.
result Proves Kazdan-Warner type theorems for polyhedral surfaces.

Improved Gaussian Process model for predicting trajectories without independence assumption errors.

problem Incorrect independence assumption in previous work on Gaussian Process uncertainty propagation.
method Proposed a novel piecewise linear approximation to correct the independence assumption in continuous models.
result Corrected the independence assumption in Gaussian Process models for predicting trajectories.

Explicit formula derived for Slepian process boundary non-crossing probabilities.

problem Calculating boundary non-crossing probabilities for Slepian processes.
method Derived explicit formula and approximation formula for general continuous boundaries.
result Easy to implement formulas for boundary non-crossing probabilities.

Two new criteria help understand the advantage of deep neural networks.

problem Understanding the advantage of deepening neural networks.
method Proposed two new criteria to evaluate the expressivity of functions computable by deep neural networks.
result Increasing layers is more effective than increasing units in improving the expressivity of deep neural networks.

New method uses DC functions for piecewise linear regression.

problem Regression with piecewise linear constraints.
method Estimates piecewise linear convex functions using a difference of convex functions.
result Method achieves close to minimax statistical risk and comparable performance to existing methods.

We obtain a criterion for approximability by embeddings of piecewise linear maps of a circle to the plane, analogous to the one proved by Minc for maps of a segment to the plane. Theorem. Let S be a triangulation of a circle with s vertices. Let f be a simplicial map of the graph S to the plane. The map f is approximab…

2008-08-08abs ↗pdf ↗

Paper proposes LANN to measure model complexity of neural networks with curve activation functions.

problem Measuring model complexity of neural networks with curve activation functions.
method Proposes LANN, a piecewise linear framework to approximate curve activation functions, and derives complexity measure based on the number of linear regions.
result Demonstrates positive correlation between overfitting and model complexity during training.

DNNs can approximate fractal functions with exponential linear regions.

problem Understanding neural network approximations of complex functions.
method Using Iterated Function Systems (IFS) and neural networks to generate fractal functions.
result DNNs can generate fractal functions with a number of linear regions exponential in the number of parameters.

Extends Tanimoto kernel to real-valued functions.

problem Measuring similarity between real-valued functions.
method Unified representation of real-valued functions via sets, derived general form of the kernel, explicit feature representation, and smooth approximation.
result General Tanimoto kernel for real-valued functions.

New CPWL functions for deep neural networks with practical applications in coding.

problem Expressivity of deep ReLU neural networks in high dimensions.
method Developed new families of CPWL functions and showed they can be computed by ReLU networks.
result Proved approximation error of CPWL functions by shallower networks and separation result.

Paper introduces \ell-DER for regression tasks using morphological operators and convex-concave procedure.

problem Developing a universal approximator for regression tasks.
method Introduces \ell-DER model, trains it using a convex-concave procedure (CCP) to minimize least-squares.
result Outperforms other hybrid morphological models and state-of-the-art approaches.

SyMPLER improves time series forecasting in nonstationary environments with explainable models.

problem Nonstationary time series forecasting with limited interpretability.
method Dynamic piecewise-linear approximations based on Statistical Learning Theory generalization bounds.
result SyMPLER achieves comparable performance to black-box and explainable models while maintaining interpretability.

Properties of a parametric curve in R^3 are often determined by analysis of its piecewise linear (PL) approximation. For Bezier curves, there are standard algorithms, known as subdivision, that recursively create PL curves that converge to the curve in distance . The exterior angles of PL curves under subdivision are s…

2012-10-09abs ↗pdf ↗

This paper studies PL cobordism categories and their homotopy types.

problem Understanding the homotopy types of PL cobordism categories.
method Introducing a bordism category and showing weak homotopy equivalence to an infinite loop space.
result The classifying space BCdPLB\mathcal{C}_d^{PL} is weak homotopy equivalent to an infinite loop space.

The preservation of ambient isotopic equivalence under piecewise linear (PL) approximation for smooth knots are prominent in molecular modeling and simulation. Sufficient conditions are given regarding: (1) Hausdorff distance, and (2) a sum of total curvature and derivative. High degree Bezier curves are often used as …

2013-12-19abs ↗pdf ↗

Estimates SDEs from sparse data using Gaussian processes.

problem Estimating drift and diffusion functions in SDEs from sparse observations.
method Gaussian processes for flexible modeling, approximate EM algorithm, sparse Gaussian process approximation.
result Accurate estimation of SDE parameters from sparse data.

Piecewise linear activations create many spurious local minima in neural networks.

problem Understanding the loss surface of neural networks with piecewise linear activations.
method Proved the existence of infinite spurious local minima and partitioned the loss surface into smooth cells.
result Piecewise linear activations create many spurious local minima that are invariant under a continuous path.

The regularization path of the Lasso can be shown to be piecewise linear, making it possible to "follow" and explicitly compute the entire path. We analyze in this paper this popular strategy, and prove that its worst case complexity is exponential in the number of variables. We then oppose this pessimistic result to a…

2012-05-01abs ↗pdf ↗

Paper finds how many neurons are needed to approximate histogram distributions.

problem How many neurons are needed to approximate a target probability distribution?
method Examined for uniform input distribution and histogram target distributions, using efficient neural net construction.
result Obtained a new upper bound on the number of required neurons, strictly better than previous bounds.

Piecewise-linear regression trees improve tree-based regression with theoretical and practical benefits.

problem Improving tree-based regression models with theoretical guarantees and practical tractability.
method Regularized piecewise-linear node-splitting criterion, LASSO-type and 2\ell_{2} regularization, variable selection procedure.
result New high-probability generalization error bounds for piecewise-linear regression trees.

Study approximates nonlinear functionals using deep ReLU networks.

problem Approximating nonlinear continuous functionals with neural networks.
method Constructs continuous piecewise linear interpolation under simple triangulation, analyzes rates of approximation.
result Established rates of approximation for functional deep ReLU networks.

New approach treats neural networks with piecewise linear activations using tropical geometry.

problem Upper bounds on linear regions of neural networks with ReLU or leaky ReLU activations.
method Treat neural network layers with piecewise linear activations as tropical polynomials, refining upper bounds using tropical geometry.
result Upper bounds on linear regions improved to $\min\left\{ 2^m, \sum_{j=0}^n \binom{m}{j} ight\}$, where n,mn, m are the number of inputs and outputs, respectively.

Paper presents ABGD for efficient piecewise linear regression in high dimensions.

problem Efficiently solving piecewise linear regression in high-dimensional spaces.
method Parametrizes piecewise linear functions as difference of max-affine functions, using ABGD algorithm.
result ABGD converges linearly to an ε-accurate estimate with optimal sample complexity.