Characterizes exchangeable feature allocations with specific probability functions.
problem Tackles the characterization of exchangeable feature allocations with product-form probability functions.
method Characterizes the class of exchangeable feature allocations using a countable matrix, sequences of weights, and a consistency condition.
result Provides a characterization of the Indian Buffet Process and Beta--Bernoulli model as the only consistent exchangeable feature allocations with product form.
Formula for computing triple-cup product from Heegaard diagrams of 3-manifolds.
problem Computing the triple-cup product invariant of 3-manifolds.
method Explicit formula from Heegaard diagrams and reduction of Turaev's homotopy intersection form.
result Triple-cup product can be recovered from Heegaard diagrams and Turaev's form.
The study examines the balancedness of random partition models and finds the rich-get-richer characteristic is a result of model assumptions.
problem The balancedness of random partition models is largely neglected in the literature.
method Formulated a framework to define and study the balancedness of exchangeable random partition models, analyzed using product-form exchangeability and projectivity assumptions.
result The 'rich-get-richer' characteristic is an inevitable consequence of the model assumptions.
We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might yield useful information about other, unobserved, parts of the MDP. We present a…
New tuning rules for Metropolis algorithms derived from Bayesian large-sample asymptotics.
problem Optimal scaling in random-walk Metropolis algorithms under realistic assumptions.
method Large-sample asymptotics to derive weak convergence results and tuning guidelines.
result Tuning guidelines consistent with previous ones when target density is product form, accounting for correlation structure.
Defines a new tensor related to special geometric spaces.
problem Understanding new curvature tensors in semi-Riemannian geometry.
method Defines a generalized curvature tensor using specific operations.
result The tensor is connected to quasi-Einstein, Roter, and Roter-type spaces.
The paper verifies deep neural networks' ability to approximate functions on spheres.
problem Theoretical verification of deep neural networks' performance on spherical functions.
method Spherical analysis using reproducing kernels and convolutional factorizations.
result Rates of uniform approximation for functions in Sobolev spaces and additive ridge forms.
We study the general geometrical structure of the coadjoint orbits of a semidirect product formed by a Lie group and a representation of this group on a vector space. The use of symplectic induction methods gives new insight into the structure of these orbits. In fact, each coadjoint orbit of such a group is obtained b…
Ozsvath and Szabo construct a spectral sequence with E_2 term Λ^*(H^1(Y;Z))\otimes Z[U,U^{-1}] converging to HF^\infty(Y,s) for a torsion Spin^c structure s. They conjecture that the differentials are completely determined by the integral triple cup product form via a proposed formula. In this paper, we prove that HF^\…
The twistor space of the sphere S^{2n} is an isotropic Grassmannian that fibers over S^{2n}. An orthogonal complex structure on a subdomain of S^{2n} (a complex structure compatible with the round metric) determines a section of this fibration with holomorphic image. In this paper, we use this correspondence to prove t…
A new framework using kernel packets overcomes limitations of state space models for multi-dimensional data.
problem Computational limitations of Gaussian process regression in large-scale applications.
method Kernel packet approach, identifying KPs via forward and backward state space representations.
result Exact, memory-efficient inference with linear-time training and logarithmic/predictive time.
The paper confirms a conjecture about Hardy-Sobolev-Maz'ya inequalities and Green's functions on hyperbolic spaces.
problem Sharp constant in Hardy-Sobolev-Maz'ya inequalities and Green's functions on hyperbolic spaces.
method Fourier analysis techniques on hyperbolic spaces and Green's function estimates.
result The sharp constant in the 2n−1-th order Hardy-Sobolev-Maz'ya inequality in the upper half space of dimension n coincides with the best 2n−1-th order Sobolev constant when n is odd and n≥9. We study two special cases of the equivariant index defined in part I of this series. We apply this index to deformations of Spinc-Dirac operators, invariant under actions by possibly noncompact groups, with possibly noncompact orbit spaces. One special case is an index defined in terms of multiplicities of discrete…
We consider an arbitrary linear elliptic first--order differential operator A with smooth coefficients acting between sections of complex vector bundles E,F over a compact smooth manifold M with smooth boundary N. We describe the analytic and topological properties of A in a collar neighborhood U of N and analyze vario…
Let G be a finite group and let M be a G-manifold. We introduce the concept of generalized orbifold invariants of M/G associated to an arbitrary group Gamma, an arbitrary Gamma-set, and an arbitrary covering space of a connected manifold Sigma whose fundamental group is Gamma. Our orbifold invariants have a natural and…
NANSDE-Net models time series with memory using neural ARMA-type noise.
problem Modeling time series with long- or short-memory characteristics.
method Developed NANSDE-Net, a generative model that incorporates Neural Network-kernel ARMA-type noise.
result NANSDE-Net matches or outperforms existing models in reproducing long- and short-memory features of data.
We give an integral representaion of the zeta-reguralized determinant of Laplacians on three dimensional Heisenberg manifolds, and study a behaivior of the values when we deform the uniform discrete subgroups. Heiseberg manifolds are the total space of a fiber bundle with a torus as the base space and a circle as a typ…
This research shows how quadratic models can recover tensors with fewer samples than traditional methods.
problem Predicting missing entries in tensors with limited observations.
method Examined non-convex methods for learning quadratic models and their sample complexity.
result All local minima of the mean squared error objective are global minima, recovering the original tensor with linear samples.
Warped product manifolds with p-dimensional base, p=1,2, satisfy some curvature conditions of pseudosymmetry type. These conditions are formed from the metric tensor g, the Riemann-Christoffel curvature tensor R, the Ricci tensor S and the Weyl conformal curvature C of the considered manifolds. The main result of the p…
Optimizes Metropolis-Hastings algorithms for efficient sampling in high dimensions.
problem Efficiently sampling from complex target distributions in high-dimensional spaces.
method Analyzes and optimizes the Barker proposal and other locally-balanced algorithms.
result Derives optimal noise distribution and balancing function for the Barker proposal.
This paper studies iteration convergence of Kronecker graphical lasso (KGLasso) algorithms for estimating the covariance of an i.i.d. Gaussian random sample under a sparse Kronecker-product covariance model and MSE convergence rates. The KGlasso model, originally called the transposable regularized covariance model by …
Functional approach calculates path probabilities in stochastic motion.
problem Calculating path probabilities in stochastic motion.
method Functional technique applied to derive path probability distribution.
result General formula derived for path probability distribution.
Bayesian approach approximates probability functions of Gaussian mixtures.
problem Approximating probability functions of non-spherical Gaussian mixtures.
method Bayesian decomposition, spherical radial decomposition, random sampling.
result Established differentiability and integral representation of gradient for probability functions.
The problem of finding the missing values of a matrix given a few of its entries, called matrix completion, has gathered a lot of attention in the recent years. Although the problem under the standard low rank assumption is NP-hard, Candès and Recht showed that it can be exactly relaxed if the number of observed entrie…
We show a general relation between the spatially disjoint product of probability density functions and the sum of their Fisher information metric tensors. We then utilise this result to give a method for constructing the probability density functions for an arbitrary Riemannian Fisher information metric tensor. We note…
Conditional probabilities modeled using Riemann-Theta Boltzmann Machines.
problem Modeling conditional probabilities in Boltzmann machines.
method Deriving conditional density functions from Riemann-Theta Boltzmann machines.
result Conditional densities can be directly inferred from Riemann-Theta Boltzmann machines.
Optimal insurance minimizes ruin probability with non-decreasing functions.
problem Minimizing ruin probability with insurance premiums and non-decreasing functions.
method Reformulated problem with inverse survival function as control variable.
result Deductible insurance with maximum limit is optimal.
Paper shows Dirac kernels simplify estimating binary probability distributions.
problem Estimating unknown probability distributions for binary inputs.
method Expanding estimation in Rademacher-Walsh Polynomial basis functions, then showing equivalence to Dirac kernels.
result Dirac kernels can improve computational efficiency and notation for large binary input spaces.
This paper optimizes functions of probability measures using particle gradient descent for displacement convex functions.
problem Optimizing functions of probability measures with displacement convex properties.
method Particle gradient descent applied to displacement convex functions with theoretical guarantees.
result Finite number of particles and computations are sufficient to find optimal solutions for displacement convex functions.
Study on Einstein flow on product manifolds, showing recollapse and expansion behaviors.
problem Behavior of Einstein flow on product manifolds with positive cosmological constant.
method Existence of continuous families of recollapsing and expanding models, analysis of curvature conditions.
result Existence of recollapsing models with positive curvature in at least one factor.
Evidential Softmax preserves multimodality in sparse probability distributions for generative models.
problem Sparse probability distributions in deep generative models make exact marginalization computationally intractable.
method Introduce ev-softmax, a sparse normalization function that preserves multimodality and can be trained with probabilistic loss functions.
result ev-softmax outperforms existing techniques in distributional accuracy and dimensionality reduction.
Algorithm learns smooth probability functions from Bernoulli tests with guarantees.
problem Learning smooth probability functions from Bernoulli tests with contextual features.
method Scalable algorithm with rigorous L2-norm convergence guarantees for posterior update rule.
result Empirical convergence rates match theoretical guarantees, superior to state-of-the-art.
We consider returns of two Korean stock market indices, KOSPI and KOSDAQ index. Central parts of the probability distribution function of returns are well fitted by the Lorentzian distribution function. However, tail parts of the probability distribution function follow a power law behavior well. We found that the prob…
OPAA estimates probability densities using functional analysis.
problem Estimating probability density functions efficiently and accurately.
method OPAA uses a parallelizable algorithm based on functional analysis to estimate probability distributions.
result OPAA provides an efficient method to estimate probability density functions and normalizing weights.
Method estimates shared and study-specific factors for multi-study data.
problem Covariance estimation for multi-study data with shared and study-specific components.
method Spectral decomposition for latent factors, surrogate Bayesian regressions for loadings and variances.
result Strong frequentist guarantees and superior performance in simulations and real data.
Paper optimizes combining expert predictions using CRPS loss.
problem Optimizing combining expert predictions in online learning.
method Combines probabilistic forecasts using CRPS loss function in the prediction with expert advice framework.
result Time-independent upper bound for the regret of the Vovk's aggregating algorithm using CRPS as a loss function is obtained.
Tutorial on estimating SVM class probabilities.
problem Estimating class probabilities for SVM models.
method Compute implied posterior probabilities via isotonic regression.
result Calibrated implied posterior probabilities for SVMs.
Unified view of GANs, VI, RL through PFD.
problem Unified understanding of GANs, VI, RL.
method Probability Functional Descent (PFD) algorithm.
result PFD unifies GANs, VI, RL.
Study on estimating class probabilities using empirical risk minimization.
problem Estimating class probabilities within binary classification.
method Empirical risk minimization (ERM) for class probability estimation.
result The estimator converges to true class probabilities under certain conditions.
New discrepancy function compares discrete probability measures considering space geometry.
problem Comparing discrete probability measures in a geometrically meaningful way.
method Proposes the Fourier Discrepancy Function, proving convexity, differentiability, and providing gradient formula.
result Proves the Fourier Discrepancy is convex, twice differentiable, and provides an explicit gradient formula.
Study of hypersurfaces in curved spaces with specific curvature properties.
problem Characterizing hypersurfaces in spaces of constant curvature with particular curvature properties.
method Investigates hypersurfaces isometrically immersed in semi-Riemannian spaces of constant curvature, focusing on the curvature tensor and its properties.
result Hypersurfaces in the specified spaces satisfy a Roter type equation, linking their curvature tensor to specific tensor products.
In many signal detection and classification problems, we have knowledge of the distribution under each hypothesis, but not the prior probabilities. This paper is aimed at providing theory to quantify the performance of detection via estimating prior probabilities from either labeled or unlabeled training data. The erro…
Paper derives necessary optimality condition for portfolio selection with distorted probabilities.
problem Continuous-time portfolio selection with S-shaped utility and probability distortions.
method Derives necessary condition for optimality using cumulative prospective theory.
result Derives a necessary condition for optimality in a behavioral portfolio selection problem.
This study redefines probability for finite outcomes using axioms and examples.
problem Defining probability for finite outcomes and preserving information.
method Developed three axioms for relative probability functions and provided examples and a system for their composition.
result Proved the topological closure of the relative probability space, preserving information under limits.
Conventional multiclass conditional probability estimation methods, such as Fisher's discriminate analysis and logistic regression, often require restrictive distributional model assumption. In this paper, a model-free estimation method is proposed to estimate multiclass conditional probability through a series of cond…
The study evaluates Bregman divergences for learning crowd probabilities.
problem Learning crowd probabilities from global perspectives.
method Adapting machine learning models to target probability distributions using Bregman divergences.
result Special attention is needed when constructing objective functions for neural network optimization.
PGF kernels analyze spherical data using generalized RBF kernels.
problem Analysis of spherical data.
method Introduced PGF kernels and a semi-parametric learning algorithm.
result PGF kernels generalize RBF kernels for spherical data.
A method for diffusion on probability simplex for generative models.
problem Tension between continuous and discrete data in diffusion models.
method Proposes using softmax function applied to Ornstein-Uhlenbeck Process on probability simplex.
result Method extends to bounded image generation.