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.
New conditions ensure deep neural networks can approximate any function on non-Euclidean spaces.
Bayesian framework for sequential learning tasks with low-rank approximations.
Single-head attention approximates any function under various norms.
Neural ODEs and i-ResNet are recently proposed methods for enforcing invertibility of residual neural models. Having a generic technique for constructing invertible models can open new avenues for advances in learning systems, but so far the question of whether Neural ODEs and i-ResNets can model any continuous inverti…
We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embedding (GE). In contrast to IPS, that is limited to approximating positive-definite (PD) similarities, SIPS goes beyond the limitation by introd…
Transformer models can approximate smooth functions with prompts, enhancing LLMs' dynamic capabilities.
Study approximates operator learning for PDEs using Fourier multipliers.
The universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development of new theoretically justified neural network architectures and blurring our understanding of our current models' potential. This paper works towards overcoming th…
Recently, deep learning has achieved huge successes in many important applications. In our previous studies, we proposed quadratic/second-order neurons and deep quadratic neural networks. In a quadratic neuron, the inner product of a vector of data and the corresponding weights in a conventional neuron is replaced with…
New RBF networks can approximate any continuous function.
In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its implementation simplicity and low computational costs. We show its approximation and feature extracti…
A new method learns complex dynamical systems from data efficiently.
Study extends neural network approximation to time-varying PDEs using Fourier-Lebesgue spaces.
Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally efficient approximations. We showcase the usefulness of the proposed method, its eq…
In this paper, we propose a low-rank approximation method based on discrete least-squares for the approximation of a multivariate function from random, noisy-free observations. Sparsity inducing regularization techniques are used within classical algorithms for low-rank approximation in order to exploit the possible sp…
We consider the representation power of siamese-style similarity functions used in neural network-based graph embedding. The inner product similarity (IPS) with feature vectors computed via neural networks is commonly used for representing the strength of association between two nodes. However, only a little work has b…
Recently, artificial neural networks (ANNs) in conjunction with stochastic gradient descent optimization methods have been employed to approximately compute solutions of possibly rather high-dimensional partial differential equations (PDEs). Very recently, there have also been a number of rigorous mathematical results …
AI enhances financial services but humans are irreplaceable for empathy, presence, and ethics.
As a non-parametric Bayesian model which produces informative predictive distribution, Gaussian process (GP) has been widely used in various fields, like regression, classification and optimization. The cubic complexity of standard GP however leads to poor scalability, which poses challenges in the era of big data. Hen…
Paper develops SINNOs for approximating stochastic processes.
Quantum machine learning models can approximate any continuous function.
Proposes a framework to identify and correct model-form errors in nonlinear systems.
The Interaction-Transformation (IT) is a new representation for Symbolic Regression that restricts the search space into simpler, but expressive, function forms. This representation has the advantage of creating a smoother search space unlike the space generated by Expression Trees, the common representation used in Ge…
Transformers can approximate posterior predictive distributions through in-context learning.
Matrix rank minimization problem is in general NP-hard. The nuclear norm is used to substitute the rank function in many recent studies. Nevertheless, the nuclear norm approximation adds all singular values together and the approximation error may depend heavily on the magnitudes of singular values. This might restrict…
2D CNNs approximate Korobov functions with near-optimal rates.
HDNNs can approximate any continuous function, proving their expressivity.
We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded. The result holds for continuous and strictly monotonic activation functions as well as for the ReLU activation function. This complements recent results on approxima…
Study improves understanding of network degree distributions using non-linear ERGs.
Softmax attention approximates complex functions and subsumes many known universal approximators.
Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go beyond the mean field approximation and yields good uncertainty on the …
We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of theoretical analyses of deep learning has revealed its high expressive power and unive…
This study uses neural networks to approximate Bayesian filtering problems.
Affine spiking neural networks learn efficiently and generalize well.
Reduced modeling of a computationally demanding dynamical system aims at approximating its trajectories, while optimizing the trade-off between accuracy and computational complexity. In this work, we propose to achieve such an approximation by first embedding the trajectories in a reproducing kernel Hilbert space (RKHS…
Paper interprets ResNets via gate-network controls and deep-layer classifications.
PLN-Nets with two linear layers and parallel LN achieve universal approximation.
Deep neural nets approximate random dynamical system trajectories uniformly in time.
New study shows exponential sample growth for ReQU neural networks.
There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximatio…
Deep neural nets solve high-dim PDEs with boundary conditions.
Develops wavelet-based neural network approximation theory.
In this paper we introduce a new neural architecture for sorting unordered sequences where the correct sequence order is not easily defined but must rather be inferred from training data. We refer to this architecture as OrderNet and describe how it was constructed to be naturally permutation equivariant while still al…
New CFNN architecture approximates functions with machine accuracy.
In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove that a shallow neural network with a sigmoid, ReLU, ELU, Softplus, or LeakyReLU act…
A new DL framework preserves geometric structures for causal predictions.
Gradient descent trains shallow neural networks to approximate functions in 1D.
Dense neural networks can't approximate all functions.