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.

168,695 papers · 148 categories

Trend · papers per month

163326488651 · Jun 202019922001200920172026
48 results for rectified functions

We extend rectified flow to infinite-dimensional Hilbert space.

problem Extending rectified flow to infinite-dimensional spaces.
method Established a rigorous functional formulation using the superposition principle for continuity equations.
result Demonstrated superior performance compared to existing models.

In this paper, we introduce a new class of curves αcalled a f-rectifying curves, which its f-position vector defined by α_{f}(s)=\int f(s)T(s)ds always lie in the rectifying plane of α, where f is an integrable function and T is the speed curve of α. In particular case, when the function f=0 or constant, the class of f…

2018-10-21abs ↗pdf ↗

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear unit (PReLU) and a new randomized leaky rectified linear units (RReLU). We evalu…

2015-05-05abs ↗pdf ↗

Study local minimizers of Ginzburg-Landau functionals in high dimensions, showing energy measures converge to rectifiable measures.

problem Investigating minimizers of Ginzburg-Landau functionals in high dimensions with energy bounds.
method Analyzing minimizers with logarithmic energy bounds and considering the vacuum manifold's homotopy classes.
result Normalized energy measures converge to an (n2)(n-2)-rectifiable measure associated with a stationary varifold.

Paper proposes a new activation function to reduce overfitting and large weight update issues.

problem Overfitting and large weight update problems in neural networks.
method Introduces a new activation function called Thresholded Exponential Rectified Linear Units (TERELU).
result TERELU shows better performance in reducing overfitting and large weight update issues compared to other activation functions.

The paper generalizes rectifying and normal curves in Lorentzian n-space.

problem Characterizing and classifying gg-rectifying and gg-normal curves in Lorentzian n-space.
method Introducing a gg-position vector field and defining gg-rectifying and gg-normal curves based on this field.
result Comprehensive characterization and classification of gg-rectifying and gg-normal curves.

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …

2017-03-30abs ↗pdf ↗

Study rectifying submanifolds with anti-torqued axis in Riemannian manifolds.

problem Characterize submanifolds with anti-torqued axis in Riemannian manifolds.
method Determine necessary and sufficient conditions for anti-torqued vector fields, characterize submanifolds, and derive rectifying submanifolds as warped products.
result Rectifying submanifolds with anti-torqued axis are warped products with specific warping functions.

The paper shows how to make certain sets on a sphere smooth and flat.

problem Understanding the smoothness of level-sets of distance functions on spheres.
method Isometric embedding into Rn+2\mathbf{R}^{n+2}, and analysis on codimension-2 graphs.
result Level-sets of distance functions on spheres are C1,1C^{1,1}-rectifiable.

The rectified flow method is analyzed for its statistical properties.

problem Theoretical support for rectified flow methods is lacking.
method Empirical analysis of rectified flow's statistical properties using regression and density estimation.
result Convergence rates for rectified flow estimators are faster than for nonparametric regression and density estimation.

The paper characterizes curves in pseudo-Galilean 4-space.

problem Characterizing curves in the pseudo-Galilean 4-space G14G_{1}^{4}.
method Investigation and characterisation of admissible curves in terms of curvature functions.
result Necessary and sufficient conditions for admissible rectifying curves in G14G_{1}^{4}.

This paper studies rectifiability in Carnot groups and proves geometric area formulas.

problem The study of rectifiability in Carnot groups and related geometric properties.
method Analysis of rectifiable measures in Carnot groups, geometric area formulas, and rectifiability of geodesic spheres.
result Geometric area formula for the centered Hausdorff measure restricted to intrinsically differentiable graphs in Carnot groups.

We introduce a notion of rectifiability modeled on Carnot groups. Precisely, we say that a subset E of a Carnot group M and N is a subgroup of M, we say E is N-rectifiable if it is the Lipschitz image of a positive measure subset of N. First, we discuss the implications of N-rectifiability, where N is a Carnot group (n…

2000-04-11abs ↗pdf ↗

A new acquisition function RMES improves Bayesian optimization performance.

problem Improper evaluation of mutual information in MES leads to suboptimal performance.
method Developed rectified MES (RMES) and used stochastic gradient ascent with reparameterization.
result RMES shows consistent improvement over MES in benchmarks and real-world problems.

A space curve in a Euclidean 3-space E3\mathbb E^3 is called a rectifying curve if its position vector field always lies in its rectifying plane. This notion of rectifying curves was introduced by the author in [Amer. Math. Monthly {\bf 110} (2003), no. 2, 147-152]. In this present article, we introduce and study the n…

2016-07-28abs ↗pdf ↗

A new method for optimal transport using neural ODEs that preserves marginal constraints.

problem Optimal transport between two continuous distributions with specific cost functions.
method Iterative construction of neural ODEs to minimize transport cost while preserving marginal constraints.
result Monotonic interior approach that decreases transport cost efficiently.

Harmonic maps to Euclidean buildings have rectifiable singular strata.

problem Understanding the structure of singular points for harmonic maps.
method Defining singular strata and proving rectifiability using the rectifiable Reifenberg program.
result Rectifiability of singular strata for harmonic maps into FF-connected complexes.

We prove (without using Federer's structure theorem) that a finite-mass flat chain over any coefficient group is rectifiable if and only if almost all of its 0-dimensional slices are rectifiable. This implies that every flat chain of finite mass and finite size is rectifiable. It also leads to a simple necessary and su…

1999-07-01abs ↗pdf ↗

A neural network with a single hidden layer can't represent certain multivariable functions.

problem Representing certain multivariable functions with a neural network having only one hidden layer.
method Developed a continuum version of a one-hidden-layer neural network with ReLU activation, and proved constraints on its parameters and second derivative.
result Existence of a smooth binary function that cannot be precisely represented by any such neural network.

AReLU uses attention-based rectification to improve neural network performance.

problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.

Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…

2016-04-07abs ↗pdf ↗

New methods for solving hydrodynamic-type equations using quasi-rectifiable Lie algebras.

problem Solving systems of hydrodynamic-type equations.
method Introducing and analyzing quasi-rectifiable Lie algebras and vector fields.
result New methods for solving hydrodynamic-type equations.

Paper tackles constrained bandit problems with a new learning framework.

problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.

Neural networks can approximate rectifiable measures with small error.

problem Approximating complex rectifiable measures using neural networks.
method Using ReLU neural networks to approximate (countably) m-rectifiable measures as push-forwards of the Lebesgue measure.
result The approximation error in terms of Wasserstein distance can be made arbitrarily small.

We show that C^1 hypersurfaces in the Heisenberg group are countably N-rectifiable. As a corollary, this shows that all C^1_H graphs over the xy-plane are countable N-rectifiable, showing the equivalence of this notion of rectifiability with that of Franchi, Serra Cassano and Serapioni for such surfaces.

2004-07-13abs ↗pdf ↗

New framework explains deep neural networks using variational spline theory.

problem Understanding functions learned by deep neural networks.
method Developed a variational framework and function space.
result Deep ReLU networks are solutions to regularized data fitting problems over the proposed function space.

Let ΛΛ be the limit set of a conformal dynamical system, i.e. a Kleinian group acting on either finite- or infinite-dimensional real Hilbert space, a conformal iterated function system, or a rational function. We give an easily expressible sufficient condition, requiring that the limit set is not too much bigger than …

2015-04-07abs ↗pdf ↗

Study on singularities in area-minimizing currents, proving unique tangent cones and rectifiability.

problem Understanding singularities in area-minimizing currents.
method Fine excess decay theorems and almost monotonicity of a frequency function.
result Unique tangent cones and countably (m2)(m-2)-rectifiable singular set.

In Heisenberg groups, rectifiability is studied for subsets using C1,αC^{1,α}-regular surfaces.

problem Understanding rectifiability of subsets in Heisenberg groups.
method Introducing a new notion of rectifiability and proving conditions for rectifiability using tangent paraboloids.
result A sufficient condition for C1,αC^{1,α}-rectifiability of low-codimensional subsets in Heisenberg groups is the existence of suitable approximate tangent paraboloids.

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.

The paper characterizes rectifying curves on smooth surfaces using isometries and Darboux frames.

problem Characterizing rectifying curves on smooth surfaces under isometries.
method Using Darboux frames and isometries to investigate rectifying curves.
result Find deviations of rectifying curves under isometries and analyze their properties.

Rectified flows achieve optimal sample complexity for generating data.

problem Generating high-quality data samples efficiently.
method Rectified flows constrain transport trajectories to be linear, enabling efficient sampling.
result Achieve sample complexity of ildeO(ε2) ilde{O}(\varepsilon^{-2}), matching optimal rate for mean estimation.

The paper explores rectified flows and their relation to optimal transport.

problem Understanding the connection between rectified flows and optimal transport.
method Investigates invariance properties, explicit constructions, and analysis of rectified flows in various settings.
result Rectified flows, when gradient constrained, do not generally solve optimal transport problems.