arXiv research

Paper proposes Sinkformers for Transformers with doubly stochastic attention.

Geometric approach for unsupervised word embedding alignment.

Graph alignment problem solved with convex relaxations for correlated matrices.

π-GNN learns soft permutations for graph representations, improving graph classification and regression.

New algorithms learn graph structures privately, matching best results.

Accelerates Birkhoff projection for manifold-constrained hyper-connections with high accuracy and speed.

Doubly-stochastic normalization improves robustness to heteroskedastic noise.

Many matching, tracking, sorting, and ranking problems require probabilistic reasoning about possible permutations, a set that grows factorially with dimension. Combinatorial optimization algorithms may enable efficient point estimation, but fully Bayesian inference poses a severe challenge in this high-dimensional, di…

In this letter, we introduce a distributed Nesterov method, termed as $\mathcal{ABN}$, that does not require doubly-stochastic weight matrices. Instead, the implementation is based on a simultaneous application of both row- and column-stochastic weights that makes this method applicable to arbitrary (strongly-connected…

We propose an efficient method for estimating covariate effects in doubly-stochastic spatial models.

This technical report proves components consistency for the Doubly Stochastic Dirichlet Process with exponential convergence of posterior probability. We also present the fundamental properties for DSDP as well as inference algorithms. Simulation toy experiment and real-world experiment results for single and multi-clu…

The paper offers new methods to determine if certain 3D links can be formed by intersecting spheres in 4D space.

Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given cost, over the space of doubly stochastic matrices. When the entropy regularization is added to the problem, the transportation plan can be…

Doubly SGD improves convergence for intractable objective optimization.

Deep kernel processes unify various models using Gram matrices and kernel functions.

New method reduces variance in complex probabilistic model optimization.

A new method for deep Wishart processes improves kernel-based models.

FDSKL algorithm trains vertically partitioned data with kernels securely and efficiently.

It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular…

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy …

This paper discusses properties of a Doubly Stochastic Poisson Process (DSPP) where the intensity process belongs to a class of affine diffusions. For any intensity process from this class we derive an analytical expression for probability distribution functions of the corresponding DSPP. A specification of our results…

The stochastic gradient descent has been widely used for solving composite optimization problems in big data analyses. Many algorithms and convergence properties have been developed. The composite functions were convex primarily and gradually nonconvex composite functions have been adopted to obtain more desirable prop…

The paper improves boundary detection and density estimation on noisy data.

When training a machine learning model with observational data, it is often encountered that some values are systemically missing. Learning from the incomplete data in which the missingness depends on some covariates may lead to biased estimation of parameters and even harm the fairness of decision outcome. This paper …

Doubly stochastic learning algorithms are scalable kernel methods that perform very well in practice. However, their generalization properties are not well understood and their analysis is challenging since the corresponding learning sequence may not be in the hypothesis space induced by the kernel. In this paper, we p…

Proposes a new method to improve regression models with reweighted samples.

We study a doubly reflected backward stochastic differential equation (BSDE) with integrable parameters and the related Dynkin game. When the lower obstacle $L$ and the upper obstacle $U$ of the equation are completely separated, we construct a unique solution of the doubly reflected BSDE by pasting local solutions and…

Robustly infers manifold density and geometry under high-dimensional noise.

DSVNP uses global and local latent variables for improved neural process predictions.

The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales up kernel methods using a novel concept called "doubly stochastic functional grad…

We introduce a doubly stochastic proximal gradient algorithm for optimizing a finite average of smooth convex functions, whose gradients depend on numerically expensive expectations. Our main motivation is the acceleration of the optimization of the regularized Cox partial-likelihood (the core model used in survival an…

Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to over-fitting, and provide well-calibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multi-layer generalisations of GPs, but inference in these models has proved challenging. Existing approaches to infe…

ADSGD method speeds up model identification in sparse optimization.

The paper studies stochastic optimization on matrices and its limits as dimensions grow.

We propose a doubly stochastic primal-dual coordinate optimization algorithm for empirical risk minimization, which can be formulated as a bilinear saddle-point problem. In each iteration, our method randomly samples a block of coordinates of the primal and dual solutions to update. The linear convergence of our method…

S2M optimizes mining for diverse data subpopulations.

Estimates outcomes under hypothetical scenarios using a flexible framework.

Proposes a new simulator for complex arrival processes.

A novel approach models rating transitions using Lie groups and Deep Learning.

Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional to a polynomial function of the context dimension, $d$. In many applications ho…

This article provides the mathematical foundation for stochastically continuous affine processes on the cone of positive semidefinite symmetric matrices. This analysis has been motivated by a large and growing use of matrix-valued affine processes in finance, including multi-asset option pricing with stochastic volatil…

The paper examines Einstein doubly warped product manifolds with a semi-symmetric metric connection.

Characterizes spacetimes using doubly torqued vectors.

New invariant measures doubly slice links, disproving previous bounds.

Enhances DGPs with adaptive RKHS Fourier features for better non-stationary pattern modeling.

Characterizes a specific type of spacetime using vector fields.

Paper characterizes nc-rank using gradient flow on symmetric space.

Characterizes and examines gradient solitons on doubly warped product manifolds.