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.
Algorithm learns similarities to optimize bandit decisions in unknown metric space.
A novel GPUM constructs Gaussian Processes for unknown manifolds with probabilistic metrics.
Researchers reconstruct simple Riemannian manifolds from boundary wave arrival times.
New algorithm detects changes in Markov kernels with unknown post-change kernel.
We establish a regularity result for the metric on any 4-dimensional extremal Kähler manifold, and a weak compactness theorem on the space of such metrics. Specifically, the sectional curvature at a point is bounded when the quantity $L^2(|\Riem|)$ in a surrounding ball is sufficiently small compared to the pointwise n…
We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…
We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite sample rates, previous approaches to classification with unknown class-conditiona…
In Theorem 1, we generalize the results of Szabo for Berwald metrics that are not necessary strictly convex: we show that for every Berwald metric F there always exists a Riemannian metric affine equivalent to F. As an application we show (Corollary 3) that every Berwald projectively flat metric is a Minkowski metric; …
As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as we…
We construct propose an anzatz for Spin(7) metrics as an R-bundle over closed G2 structures. These G2 structures are R3 bundles over 4-dimensional compact quaternion Kahler spaces. The inspiration for the anzatz metric comes from the Bryant-Salamon construction of G2 holonomy metrics and from the fact that the twistor …
Optimizes hard-to-optimize metrics using adaptive surrogates.
We study online reinforcement learning for finite-horizon deterministic control systems with {\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is endowed with a metric that characterizes the proximity between different states and…
Paper explores stability, regularization, and gradient flows for stochastic inverse problems.
This paper learns user preferences from comparisons using Mahalanobis metrics.
Constructs non-asymptotic confidence regions for unknown functions in RKHS.
New method tackles unknown unknowns in machine learning.
This paper studies clustering of data sequences using the k-medoids algorithm. All the data sequences are assumed to be generated from \emph{unknown} continuous distributions, which form clusters with each cluster containing a composite set of closely located distributions (based on a certain distance metric between di…
We investigate refocusing and strong refocusing of light rays in a space-time. A strongly refocusing space-time is refocusing. The converse is unknown. We construct examples of space-times which are refocusing, but not strongly so, at a particular point. These space-times are strongly refocusing at other points. The ge…
New method efficiently interpolates nonparametric density estimators.
Paper introduces method to estimate animal motion on unknown submanifolds using Koopman operator.
We address the problem of disambiguating large scale catalogs through the definition of an unknown artist clustering task. We explore the use of metric learning techniques to learn artist embeddings directly from audio, and using a dedicated homonym artists dataset, we compare our method with a recent approach that lea…
We consider spacetime to be a connected real 4-manifold equipped with a Lorentzian metric and an affine connection. The 10 independent components of the (symmetric) metric tensor and the 64 connection coefficients are the unknowns of our theory. We introduce an action which is quadratic in curvature and study the resul…
Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.
One of the key challenges of performing label prediction over a data stream concerns with the emergence of instances belonging to unobserved class labels over time. Previously, this problem has been addressed by detecting such instances and using them for appropriate classifier adaptation. The fundamental aspect of a n…
Paper discusses binary classification with metric space predictors, privacy constraints, and convergence rates.
Bayesian optimization tackles unknown search spaces with automatic expansion.
Proposes a method to learn both constraints and objective functions from data.
This paper evaluates knowledge graph completion models under the open-world assumption, revealing unexpected behavior of metrics.
Many nonparametric regressors were recently shown to converge at rates that depend only on the intrinsic dimension of data. These regressors thus escape the curse of dimension when high-dimensional data has low intrinsic dimension (e.g. a manifold). We show that k-NN regression is also adaptive to intrinsic dimension. …
Many applications, including rank aggregation, crowd-labeling, and graphon estimation, can be modeled in terms of a bivariate isotonic matrix with unknown permutations acting on its rows and/or columns. We consider the problem of estimating an unknown matrix in this class, based on noisy observations of (possibly, a su…
Geometric approach connects Burau representation to sphere metrics, identifying kernels.
Paper tackles open set domain adaptation by detecting unknown classes.
Study shows optimal rates for estimating Wasserstein metric and measures.
Proposes using equivariant generative models for compressed sensing with unknown orientations.
New construction of self-dual black holes using quadrics.
New proof for unique semi-symmetric compatible linear connection on Finsler manifolds.
We work on a 4-manifold equipped with Lorentzian metric and consider a volume-preserving diffeomorphism which is the unknown quantity of our mathematical model. The diffeomorphism defines a second Lorentzian metric , the pullback of . Motivated by elasticity theory, we introduce a Lagrangian expressed algebra…
AI agent learns to handle unknown unknown states in reinforcement learning.
A novel criterion selects optimal distance metrics for cell profile analysis.
In emerging Internet-of-Nano-Thing (IoNT), information will be embedded and conveyed in the form of molecules through complex and diffusive medias. One main challenge lies in the long-tail nature of the channel response causing inter-symbol-interference (ISI), which deteriorates the detection performance. If the channe…
RTSCV detects unknown unknowns to improve model performance.
New tool detects 'fleeting modes' causing excess risk in financial markets.
New method recovers clusters in non-convex finite metric spaces with oracle queries.
Study generalised Einstein metrics on Lie groups, classifying various types.
Paper develops PAC-Bayes bounds for unknown linear systems.
Optimizes risk measures given known marginal distributions of two unknown factors.
In this work, we study the asymptotic geometry of the mapping class group and Teichmueller space. We introduce tools for analyzing the geometry of `projection' maps from these spaces to curve complexes of subsurfaces; from this we obtain information concerning the topology of their asymptotic cones. We deduce several a…
The true distribution parameterizations of commonly used image datasets are inaccessible. Rather than designing metrics for feature spaces with unknown characteristics, we propose to measure GAN performance by evaluating on explicitly parameterized, synthetic data distributions. As a case study, we examine the performa…