A new tree method for tensor data improves regression accuracy.
problem Efficiently modeling tensor data for regression problems.
method Scalar-output regression tree models for scalar-on-tensor problems, and tensor-on-tensor problems using additive tree ensemble approaches.
result The tensor-input tree (TT) method outperforms tensor-input GP models in efficiency and accuracy.
Neural network predicts functional responses from scalar inputs.
problem Regression of functional responses with large scalar predictors and nonlinear relationships.
method Transform functional response to finite dimensions, design feed-forward neural network, modify output via objective functions, apply roughness penalty.
result Proposed neural network outperforms conventional methods in multiple scenarios.
The paper is devoted to the local classification of generic control-affine systems on an n-dimensional manifold with scalar input for any n>3 or with two inputs for n=4 and n=5, up to state-feedback transformations, preserving the affine structure. First using the Poincare series of moduli numbers we introduce the intr…
New method uses scalars to approximate physics functions.
problem Designing neural networks that respect physical symmetries.
method Parameterizing polynomial functions equivariant to various symmetries using scalars.
result Universal approximation of polynomial functions under various symmetries using scalars.
This paper introduces a new scalarization method for multi-objective optimization.
problem Efficiently optimizing multiple conflicting objectives in black box settings.
method Introduces a novel hypervolume scalarization function and uses it to approximate the hypervolume indicator metric.
result Provable convergence to the entire Pareto frontier using random scalarizations and Bayesian optimization.
Neurons predict future scalar inputs by learning top modes of lag vectors.
problem Predicting future scalar inputs with physiological delays.
method Normal Mode Decomposition to extract independently evolving modes.
result Temporal filters of neurons correspond to left eigenvectors of a generalized eigenvalue problem.
Model projection transfers convolutional network properties to feedforward networks.
problem Transferring properties between feedforward and convolutional networks.
method Unified node-level framework with tensor-valued activations, model projection.
result Projected CNN nodes inherit GFFN-style trainable structure.
The Finsleroid-Finsler space is constructed over an underlying Riemannian space by the help of a scalar g(x) and an input 1-form b of unit length. Explicit form of the entailed tensors, as well as the respective spray coefficients, is evaluated. The involutive case means the framework in which the characteristic sc…
FFBO optimizes functions as inputs and outputs, improving on existing BO methods.
problem Optimizing functions as both inputs and outputs in complex systems.
method Function-on-function Gaussian process (FFGP) model with a separable operator-valued kernel, scalar upper confidence bound (UCB) acquisition function, and scalable functional gradient ascent algorithm (FGA).
result FFBO outperforms existing methods in synthetic and real-world data.
FuncNN package enables deep learning with functional covariates.
problem Lack of software for deep learning with functional covariates.
method Developed an R package using keras architecture, introducing functions for model building, predictions, and cross-validation.
result First package for deep learning with functional covariates.
Tree-based algorithm for functional data analysis reduces generalization error.
problem Classification and regression problems with functional data.
method Constrained convex optimization for weighted functional L2 space, multiple splitting rules, and weighted integral features. result Reduces generalization error while maintaining interpretability.
We consider derivative-free black-box global optimization of expensive noisy functions, when most of the randomness in the objective is produced by a few influential scalar random inputs. We present a new Bayesian global optimization algorithm, called Stratified Bayesian Optimization (SBO), which uses this strong depen…
New BO method optimizes multiple objectives under input noise.
problem Optimizing multiple performance metrics in manufacturing processes subject to random input noise.
method Formalizes optimization of multivariate value-at-risk (MVaR) using random scalarizations.
result Significantly outperforms alternative methods in identifying robust designs.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
problem Training neural networks to mimic the complex interactions of brain neurons.
method Developed a network-in-network architecture with two-input activation functions, optimized hyperparameters, and compared to conventional ReLU networks.
result Two-input activation functions can learn soft XOR functions, improving network performance and robustness.
Enhances Gaussian process regression with multi-fidelity models and active subspaces for high-dimensional problems.
problem Data scarcity and high-dimensional input spaces with low intrinsic dimensionality.
method Employ Gaussian processes in a Bayesian setting, augmenting with low-fidelity models, and exploiting active subspaces.
result Improves model accuracy through multi-fidelity Gaussian process regression with active subspaces.
CcGAN tackles conditional image generation for continuous labels.
problem Mathematical challenges in conditioning on continuous, scalar labels.
method Proposes novel empirical losses and label input methods for continuous conditional GANs.
result CcGAN generates diverse, high-quality images from continuous labels.
FF algorithm uses goodness as a measure of input quality, derived from likelihood-ratio tests.
problem Training each layer locally with a goodness measure.
method FF algorithm uses a likelihood-ratio test to define goodness, which is the sum of squared activations normalized between layers.
result The goodness measure is a sufficient statistic for a likelihood-ratio test, explaining the FF algorithm's performance.
Evaluation of systemic risk in networks of financial institutions in general requires information of inter-institution financial exposures. In the framework of Debt Rank algorithm, we introduce an approximate method of systemic risk evaluation which requires only node properties, such as total assets and liabilities, a…
Constructs optimal symplectic connections for Kaehler metrics on holomorphic submersions.
problem Finding canonical relatively Kaehler metrics on holomorphic submersions.
method Extremal Kaehler metrics, optimal symplectic connections, and adiabatic classes.
result Constructs Kaehler metrics with constant scalar curvature and extremal metrics.
This paper presents a new mathematical framework to analyze the loss functions of deep neural networks with ReLU functions. Furthermore, as as application of this theory, we prove that the loss functions can reconstruct the inputs of the training samples up to scalar multiplication (as vectors) and can provide the numb…
Functional input neural networks approximate continuous functions on weighted spaces.
problem Approximating continuous functions on infinite-dimensional weighted spaces.
method Additive family mapping, non-linear activation, linear readouts, Stone-Weierstrass theorem.
result Global universal approximation of continuous functions on weighted spaces.
FF algorithm uses goodness as a likelihood-ratio test for scalar normalization.
problem Training each layer locally with scalar goodness.
method FF algorithm uses a likelihood-ratio test with squared goodness as the sufficient statistic.
result The FF algorithm generalizes to anisotropic and heavy-tailed populations.
Function approximation from input and output data pairs constitutes a fundamental problem in supervised learning. Deep neural networks are currently the most popular method for learning to mimic the input-output relationship of a general nonlinear system, as they have proven to be very effective in approximating comple…
Method integrates functional data into neural networks for better interpretability.
problem Integrating functional data into neural networks for improved interpretability.
method Integrates functional data into deep neural networks, visualizes dynamic weights.
result Model performs well in prediction and recovery of functional weights.
A new method learns the optimal pricing map for semiparametric dynamic pricing problems.
problem Optimizing pricing strategies in a semiparametric valuation model with unknown utility and noise.
method Developed a modular policy called ORBIT that uses a scalar pilot index, localizes a benchmark price, and learns a local polynomial approximation of the oracle price map.
result Achieves regret bound of \( \widetilde{O}\big(T^{\frac{2β-1}{4β-3}}+\sqrt{dT}\big) \) for the linear utility model and minimax sharp lower bound.
Generalizes neural network approximation to infinite-dimensional manifolds and derivatives.
problem Approximating differentiable maps on infinite-dimensional manifolds.
method Proves a weighted Nachbin theorem to establish universal approximation for differentiable maps, including derivatives.
result Linear functions of the signature can approximate path space functionals including their derivatives.
A new model predicts spatially varying inland flooding from time-varying inputs.
problem Ignoring time series and spatial correlations in flood models leads to inaccurate predictions.
method Introduced a multioutput Gaussian process model with separable kernels for functional inputs and spatial locations.
result The model provides accurate predictions of spatially varying inland flooding with minimal computational time.
In this article, we consider a stochastic numerical simulator to assess the impact of some factors on a phenomenon. The simulator is seen as a black box with inputs and outputs. The quality of a simulation, hereafter referred to as fidelity, is assumed to be tunable by means of an additional input of the simulator (e.g…
The Finsleroid--Finsler space becomes regular when the norm ∣∣b∣∣=c of the input 1-form b is taken to be an arbitrary positive scalar c(x)<1. By performing required direct evaluations, the respective spray coefficients have been obtained in a simple and transparent form. The adequate continuation into the regul…
The paper proposes a gradient-based method for multi-penalty Ridge regression.
problem Optimizing multiple regularization hyperparameters for linear regression.
method Gradient-based optimization through matrix differential calculus.
result The method outperforms traditional regularization techniques like LASSO and Ridge.
Statistical neurodynamics studies macroscopic behaviors of randomly connected neural networks. We consider a deep layered feedforward network where input signals are processed layer by layer. The manifold of input signals is embedded in a higher dimensional manifold of the next layer as a curved submanifold, provided t…
The Yamabe invariant is an invariant of a closed smooth manifold defined using conformal geometry and the scalar curvature. Recently, Petean showed that the Yamabe invariant is non-negative for all closed simply connected manifolds of dimension ≥5. We extend this to show that Yamabe invariant is non-negative for a…
GGMPs improve non-Gaussian conditional density estimation.
problem Multimodality, heteroscedasticity, and strong non-Gaussianity in conditional density estimation.
method GGMP combines local Gaussian mixture fitting, cross-input component alignment, and per-component heteroscedastic GP training.
result GGMPs improve distributional approximation on synthetic and real-world datasets.
Algorithm computes eigenvalues and eigenforms on Calabi-Yau threefolds.
problem Computing spectra of Laplace-de Rham operator on Calabi-Yau manifolds.
method Numerical algorithm using approximate Calabi-Yau metric.
result Computed eigenvalues and eigenforms for the Fermat quintic threefold.
Universal approximation theorem for differentiable maps on infinite-dimensional manifolds
problem Approximation of differentiable maps on infinite-dimensional manifolds
method Weighted universal approximation theorem
result Universal approximation theorem for differentiable maps
The paper studies the asymptotic expansion of Gaussian integral operators on Riemannian submanifolds.
problem Analyzing the asymptotic behavior of Gaussian integral operators on Riemannian submanifolds.
method Deriving a full asymptotic expansion of the Gaussian integral operator and computing the first-order correction term.
result Explicit computation of the first-order correction term in terms of mean curvature vector and scalar curvature.
In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is trained to compress, quantize and reconstruct the bit log-likelihood ratios cor…
A method for predicting signals on graphs using Gaussian processes and optimal transport.
problem Predicting signals on complex, graph-based inputs with uncertainty quantification.
method Combining regularized optimal transport, dimension reduction, and Gaussian processes indexed by graphs.
result Efficient prediction of signals on graphs with confidence intervals.
Let X be a closed m-dimensional spin manifold which admits a metric of positive scalar curvature and let Pos(X) be the space of all such metrics. For any g in Pos(X), Hitchin used the KO-valued alpha-invariant to define a homomorphism A_{n-1} from π_{n-1}(Pos(X) to KO_{m+n}. He then showed that A_0 is not 0 if m = 8k o…
Neural ODEs simplified using Chen-Fliess series for Rademacher complexity analysis.
problem Analyzing the complexity of neural ODE models.
method Using Chen-Fliess series to frame neural ODEs as infinite-width nets, where weights are signature of control input and features are Lie derivatives.
result Derived compact expressions for the Rademacher complexity of ODE models.
Quaternion-Kähler manifolds' stability and rigidity of scalar curvature studied.
problem Stability and rigidity of scalar curvature in quaternion-Kähler manifolds.
method Analysis of stability and rigidity conditions using Einstein manifold properties.
result Quaternion-Kähler manifolds of negative scalar curvature are stable and scalar curvature rigid.
Proves curvature comparison for Riemannian bands in low dimensions.
problem Curvature comparison in Riemannian bands with lower bounds.
method Uses warped products over scalar-flat manifolds with log-concave warping.
result Scalar and mean curvature comparison results proven.
Study on scalar curvature deformations in pseudohermitian manifolds.
problem Deformation of scalar curvature in pseudohermitian manifolds.
method Analogy with Riemannian manifolds, introduction of R-singular spaces, stability conditions, partial infinitesimal rigidity. result Partial infinitesimal rigidity result for scalar curvature of compact pseudohermitian manifolds.
Small Weyl infimum on 4-manifolds with positive scalar curvature.
problem Understanding scalar curvature on 4-manifolds.
method Analyzing the Weyl functional and comparing scalar and self-dual Weyl curvatures.
result The infimum of the Weyl functional is small on many 4-manifolds with positive scalar curvature.
The paper examines Randers metrics with isotropic scalar curvature properties.
problem Characterizing Randers metrics with specific scalar curvature properties.
method Analyzes properties of Randers metrics with isotropic scalar curvature.
result Proves that Randers metrics with weakly isotropic scalar curvature have isotropic S-curvature and are either Minkowskian or Riemannian. In this paper we present results on dynamic multivariate scalar risk measures, which arise in markets with transaction costs and systemic risk. Dual representations of such risk measures are presented. These are then used to obtain the main results of this paper on time consistency; namely, an equivalent recursive form…
The paper establishes bounds on scalar curvature on asymptotically flat manifolds.
problem Establishing scalar curvature bounds on asymptotically flat manifolds.
method Using Ricci-DeTurck flow and distributional scalar curvature, the paper derives bounds on scalar curvature.
result The scalar curvature lower bound under Ricci-DeTurck flow depends on the scalar curvature lower bound in the β-weak sense and time.
Minimal splitting factors help study scalar curvature constraints.
problem Scalar curvature constraints in geometry.
method Introducing minimal splitting factors with positive scalar curvature.
result Minimal splitting factors have properties similar to area minimizing hypersurfaces.