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.
Recovering matrix valued potentials from wave equation data on stationary spacetimes.
Study of metrics on positive-definite matrices from power potential, linking to power means.
Improved MMWU algorithm achieves instance-optimal regret bound for matrix LEA.
In this paper we consider a general matrix factorization model which covers a large class of existing models with many applications in areas such as machine learning and imaging sciences. To solve this possibly nonconvex, nonsmooth and non-Lipschitz problem, we develop a non-monotone alternating updating method based o…
We give a geometric construction of the multivariable Conway potential function for colored links. In the case of a single color, it is Kauffman's definition of the Conway polynomial in terms of a Seifert matrix.
We introduce a novel class of localized atomic environment representations, based upon the Coulomb matrix. By combining these functions with the Gaussian approximation potential approach, we present LC-GAP, a new system for generating atomic potentials through machine learning (ML). Tests on the QM7, QM7b and GDB9 biom…
SNS accelerates Sinkhorn algorithm with sparse Newton iterations.
In this paper, we examine the problem of approximating a general linear dimensionality reduction (LDR) operator, represented as a matrix with , by a partial circulant matrix with rows related by circular shifts. Partial circulant matrices admit fast implementations via Fourier tra…
Paper shows no spurious local minima in a specific matrix factorization problem.
Improved Bayesian regret bound for linear Thompson sampling with general distributions.
We consider the Frobenius algebra of functions on the critical set of the master function of a weighted arrangement of hyperplanes in $\C^k$ with normal crossings. We construct two potential functions (of first and second kind) of variables labeled by hyperplanes of the arrangement and prove that the matrix coefficient…
The problem of low rank matrix completion is considered in this paper. To exploit the underlying low-rank structure of the data matrix, we propose a hierarchical Gaussian prior model, where columns of the low-rank matrix are assumed to follow a Gaussian distribution with zero mean and a common precision matrix, and a W…
New algorithm improves game learning with randomised optimism.
New methods improve online matrix optimization with reduced computational cost.
We are concerned with an approximation problem for a symmetric positive semidefinite matrix due to motivation from a class of nonlinear machine learning methods. We discuss an approximation approach that we call {matrix ridge approximation}. In particular, we define the matrix ridge approximation as an incomplete matri…
New method improves matrix completion with functional maps.
We study the modularity of the genus zero open Gromov-Witten potentials and its generating matrix factorizations for elliptic orbifolds. These objects constructed by Lagrangian Floer theory are a priori well-defined only around the large volume limit. It follows from modularity that they can be analytically continued o…
Study of discrete period matrices on embedded graphs, relating to Riemann surfaces.
A new method clusters rows of a matrix of point processes.
Paper develops new patterns for unique matrix completions.
Study improves Calderón problem for systems, uniquely determining connections and potentials.
SNN architecture shows gradient descent converges to regularized solution in matrix sensing problems.
Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting…
We propose a route for the evaluation of risk based on a transformation of the covariance matrix. The approach uses a `potential' or `objective' function. This allows us to rescale data from different assets (or sources) such that each data set then has similar statistical properties in terms of their probability distr…
Transformers interpreted as probabilistic Laplacian Eigenmaps steps.
Improved matrix completion for non-uniformly sampled data.
In the probabilistic topic models, the quantity of interest---a low-rank matrix consisting of topic vectors---is hidden in the text corpus matrix, masked by noise, and the Singular Value Decomposition (SVD) is a potentially useful tool for learning such a low-rank matrix. However, the connection between this low-rank m…
Paper proposes iLPA for solving DC composite optimization problems, with applications to matrix completion with outliers.
Non-negative matrix factorization is a popular tool for decomposing data into feature and weight matrices under non-negativity constraints. It enjoys practical success but is poorly understood theoretically. This paper proposes an algorithm that alternates between decoding the weights and updating the features, and sho…
We provide a proof of backpropagation algorithm in matrix notation.
New integrable matrix PDEs derived from Frölicher-Nijenhuis brackets.
Low-rank matrix factorizations arise in a wide variety of applications -- including recommendation systems, topic models, and source separation, to name just a few. In these and many other applications, it has been widely noted that by incorporating temporal information and allowing for the possibility of time-varying …
We investigate solutions of the elliptic sinh-Gordon equation of spectral genus g<3. These solutions are parametrized by complex matrix-valued polynomials called potentials. On the space of these potentials there act two commuting flows. The orbits of these flows are called Polynomial Killing fields and are double peri…
Second-order optimization methods such as natural gradient descent have the potential to speed up training of neural networks by correcting for the curvature of the loss function. Unfortunately, the exact natural gradient is impractical to compute for large models, and most approximations either require an expensive it…
Optimistic estimate predicts best fitting performance of nonlinear models.
Matrix H-theory models stock market fluctuations using hierarchical multivariate distributions.
We address the collective matrix completion problem of jointly recovering a collection of matrices with shared structure from partial (and potentially noisy) observations. To ensure well--posedness of the problem, we impose a joint low rank structure, wherein each component matrix is low rank and the latent space of th…
The paper introduces a new class of multivariate mixtures for actuarial applications.
The study uses a ReLU network to discern geometric structure in data via the Data Information Matrix.
SMM preserves matrix data structure for SVM classification.
This work explores how feature decorrelation improves self-supervised learning.
Data often comes in the form of an array or matrix. Matrix factorization techniques attempt to recover missing or corrupted entries by assuming that the matrix can be written as the product of two low-rank matrices. In other words, matrix factorization approximates the entries of the matrix by a simple, fixed function-…
One major challenge for the legacy measurements at the LHC is that the likelihood function is not tractable when the collected data is high-dimensional and the detector response has to be modeled. We review how different analysis strategies solve this issue, including the traditional histogram approach used in most par…
New method corrects bias in missing data for matrix completion.
In this paper, we develop an approach to recursively estimate the quadratic risk for matrix recovery problems regularized with spectral functions. Toward this end, in the spirit of the SURE theory, a key step is to compute the (weak) derivative and divergence of a solution with respect to the observations. As such a so…
Proposes CAL to learn causal adjacency for better spatiotemporal prediction.
Muon optimizer simplifies matrix optimization with spectral orthogonalization.
New proof shows norms can't explain deep learning's implicit regularization.