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

132263395526 · Jun 202019922001200920172026
48 results for bounded power

It is well-known that quasi-isometries between R-trees induce power quasi-symmetric homeomorphisms between their ultrametric end spaces. This paper investigates power quasi-symmetric homeomorphisms between bounded, complete, uniformly perfect, ultrametric spaces (i.e., those ultrametric spaces arising up to similarity …

2010-02-08abs ↗pdf ↗

The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth and width. These bounds improve upon state-of-the-art bounds for certain classes o…

2018-06-29abs ↗pdf ↗

Recently, Sogge-Zelditch and Colding-Minicozzi gave new power law lower bounds on the size of the nodal sets of eigenfunctions. The purpose of this short note is to point out a third method to obtain a power law lower bound on the volume of the nodal sets. Our method is based on the Donnelly-Fefferman growth bound for …

2010-10-21abs ↗pdf ↗

Sharp lower bound found for integral varifolds' mean curvature.

problem Finding a sharp lower bound for the mean curvature integral of integral varifolds.
method Developed a new approach using integral varifolds and mean curvature.
result A sharp lower bound on the mean curvature integral with critical power for integral varifolds.

New framework for tracking varying bounds in time series forecasting.

problem Forecasting bounded time series with varying bounds.
method Extended log-likelihood estimation, online maximum likelihood estimation, Normalized Gradient Descent (NGD) for quasiconvex optimization.
result Derive an Online Normalized Gradient Descent algorithm for online bound tracking.

New method estimates log-determinant using trace powers, avoiding classical limitations.

problem Estimating log-determinant of large matrices efficiently and accurately.
method Interpolating moment-generating function and its derivative at zero using trace powers.
result No continuous estimator using finite moments can be uniformly accurate over unbounded conditioning.

Homotopy equivalences of 3-manifolds have a bounded power.

problem Understanding the behavior of self-homotopy equivalences of 3-manifolds.
method Proving the existence of a constant AMA_M for every self-homotopy equivalence ff of a 3-manifold MM such that fkf^k is homotopic to a homeomorphism for some integer kk.
result There exists a constant AMA_M depending only on the manifold MM such that for every self-homotopy equivalence ff of MM, there is an integer kk with 1kAM1 \leq k \leq A_M for which fkf^k is homotopic to a homeomorphism.

We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over …

2016-02-23abs ↗pdf ↗

CR invariant differential operators on densities with leading part a power of the sub-Laplacian are derived. One family of such operators is constructed from the ``conformally invariant powers of the Laplacian'' via the Fefferman metric; the powers which arise for these operators are bounded in terms of the dimension. …

2003-01-09abs ↗pdf ↗

Study improves treatment effect estimation using unlabeled covariates.

problem Estimating treatment effects with limited labeled data.
method Developed efficiency bounds and estimators for semi-supervised setting.
result Estimators using unlabeled covariates have lower asymptotic variance.

Study shows limits of certain normalizing flows in higher dimensions.

problem Understanding the representation power of normalizing flows in different dimensions.
method Rigorously established bounds on expressive power of basic normalizing flows.
result Limited representation power in higher dimensions, especially with moderate depth.

A permutation-based SW test achieves minimax-optimal power for two-sample testing.

problem Nonparametric two-sample testing using the sliced Wasserstein distance.
method Proposes a permutation-based SW test and analyzes its performance.
result Achieves minimax separation rate n1/2n^{-1/2} over multinomial and bounded-support alternatives.

The paper studies volumes of direct images for high tensor powers of ample bundles.

problem Understanding asymptotics of Monge-Ampère volumes for high tensor powers of ample line bundles.
method Analyzes the leading term of asymptotics and classifies bundles saturating a topological bound.
result Provides a characterization of bundles admitting projectively flat Hermitian structures in the case of high symmetric powers of ample vector bundles.

Paper proposes GPM for simultaneous community detection and group synchronization.

problem Simultaneous community detection and group synchronization in networks.
method Generalized Power Method (GPM) for non-convex optimization.
result GPM achieves exact recovery in O(nlog2n)O(n\log^2n) time, outperforming SDP.

Study L2L^{2}-harmonic forms on almost Kähler manifolds, extending vanishing theorems.

problem Analyzing L2L^{2}-harmonic forms on complete almost Kähler manifolds.
method Decomposing L2L^{2}-harmonic forms into Lefschetz powers of primitive forms, extending vanishing theorems.
result Spaces of harmonic (p,q)(p,q)-forms on XX vanish unless p+q=np+q=n.

Improved bounds on acylindricity for right-angled Artin groups.

problem Bounding the acylindrical action of right-angled Artin groups on their extension graphs.
method Exploring lattice properties, studying prefixes of powers, and extending quasi-root uniqueness.
result Cardinality of rr-quasi-stabilizer is bounded by a linear function of rr.

Introduces spectral-domain Wasserstein distance and Gelbrich bound for elliptical processes.

problem Estimating distances and bounds for elliptical stochastic processes.
method Defines spectral-domain W2\mathcal{W}_2 Wasserstein distance and Gelbrich bound.
result Develops new spectral-domain bounds for non-elliptical processes.

Sharp analysis of power iteration for tensor PCA, improving convergence and stopping criteria.

problem Analyzing the power iteration algorithm for tensor PCA to improve convergence and stopping criteria.
method Sharp bounds on the number of iterations, revealing a smaller algorithmic threshold, proposing a stopping criterion.
result Sharp bounds on the number of iterations required for power method to converge, revealing a smaller algorithmic threshold than previously conjectured.

Study spectral learning for odeco tensors, addressing initialization bottlenecks.

problem Recovering orthogonally decomposable tensors under noise.
method Investigates perturbation bounds, non-convex optimization, and initialization strategies.
result Initialization is the main bottleneck for efficient algorithms.

Optimizes energy efficiency in wireless sensor networks with limited information.

problem Maximizing energy efficiency in energy harvesting wireless sensor networks with limited channel state information.
method Modeling as a Multi-Armed Bandits problem and developing an Upper Confidence Bound algorithm.
result Significant gains in energy efficiency compared to benchmark schemes.

Study the Bochner-Schrödinger operator's trace in semiclassical limit.

problem Trace formula for Bochner-Schrödinger operator on tensor powers of line and vector bundles.
method Semiclassical analysis of the Bochner-Schrödinger operator HpH_p on tensor powers of a Hermitian line bundle and vector bundle.
result Complete asymptotic expansion of the trace of φ(Hp)\varphi(H_p) in the semiclassical limit pop o \infty.

The paper proves geometric and spectral alignment for deep neural networks.

problem Understanding the singular spectra of deep neural network layers.
method Proves deterministic quotient-geometric estimates for singular spectra of Frobenius-normalized layer factors.
result Exact power-law spectra form a trace-normalized Cartan orbit under Frobenius normalization.

Randomly initialized ReLU networks of depth two can approximate smooth functions well.

problem Approximation power of two-layer networks of random ReLUs.
method Harmonic analysis and ridgelet representation theory for upper bounds, dimensionality arguments for lower bounds.
result Near-matching upper and lower bounds for L2L_2-approximation and Sobolev norms.

A robust model handles up to 25% of outliers in time-series data for power flow calculations.

problem Handling outliers in time-series data for accurate power flow calculations.
method Robust data-driven process model with Schweppe-type generalized maximum likelihood estimator and projection statistics for outlier weighting.
result The model can handle up to 25% of outliers in the training data set.

This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.

problem The impact of enforcing equivariance constraints on the expressive power of neural networks.
method Examined 2-layer ReLU networks, analyzed boundary hyperplanes and channel vectors, and constructed upper bounds on model size required for compensation.
result Enforcing equivariance constraints reduces the expressive power of neural networks, but this can be compensated by increasing model size.

Paper studies deep learning for solving elliptic PDEs, proving optimal bounds and neural scaling laws.

problem Solving elliptic PDEs from random samples using machine learning.
method Deep Ritz Method and Physics-Informed Neural Networks (PINNs) for the Schrödinger equation.
result Proves minimax optimal bounds and neural scaling laws for deep PDE solvers.

Estimation of functions of d d variables is considered using ridge combinations of the form k=1mc1,kφ(j=1dc0,j,kxjbk) \textstyle\sum_{k=1}^m c_{1,k} φ(\textstyle\sum_{j=1}^d c_{0,j,k}x_j-b_k) where the activation function φ φ is a function with bounded value and derivative. These include single-hidden layer neural networks, polynomials, …

2017-02-09abs ↗pdf ↗

kth-order invariant graph networks are as powerful as kth-order WL in distinguishing graphs.

problem Measuring the expressive power of graph neural network formalisms.
method Considered kth-order invariant graph networks (k-IGNs) and compared their expressive power to kth-order WL.
result k-IGNs and k-WL are equally powerful in distinguishing graphs.

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate the complexities with constraint on the expected norm to the corresponding ones with constraint on the empirical norm. This result is convenient to apply in real applications and could yield re…

2015-10-06abs ↗pdf ↗

Unified approach combines prediction-powered inference and variance reduction for semi-supervised optimization.

problem Scarcity of labeled data in semi-supervised optimization.
method PPI-SVRG, combining PPI and SVRG methods.
result Unified convergence bound with improved performance under label scarcity.

The paper derives Cramer-Rao bounds for Laplacian matrix estimation under various constraints.

problem Estimating Laplacian matrices with structural constraints and sparsity.
method Linear reparametrization and closed-form expressions for Cramer-Rao bounds tailored to Laplacian matrix estimation.
result The derived CRBs provide performance limits for Laplacian matrix estimation and are validated in various applications.