arXiv research

Improves Graph Convolutional Network performance on citation datasets.

New $k$-step policy gradient method avoids local optima in restricted policy classes.

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

K-AVG improves convergence for nonconvex optimization problems.

Algorithm improves resource allocation for food outreach to homeless.

Max-convolution is an important problem closely resembling standard convolution; as such, max-convolution occurs frequently across many fields. Here we extend the method with fastest known worst-case runtime, which can be applied to nonnegative vectors by numerically approximating the Chebyshev norm $\| \cdot \|_\infty…

Dual-T method improves transition matrix estimation in noisy label learning.

This paper identifies and estimates the label noise transition matrix without ground truth labels.

Method estimates noise transition matrix from noisy labels without relying on unreliable class-posterior estimation.

New method improves robustness of deep learning with noisy labels.

A method to learn transition matrices without anchor points improves classifier performance.

New method tightens spectral bounds for percolation in clustered networks.

We prove some stability results for smooth H-minimal hypersurfaces immersed in a sub-Riemannian k-step Carnot group G. The main tools are the formulas for the 1st and 2nd variation of the H-perimeter measure.

Let $\GG$ be a sub-Riemannian $k$-step Carnot group of homogeneous dimension $Q$. In this paper, we shall prove several geometric inequalities concerning smooth hypersurfaces (i.e. codimension one submanifolds) immersed in $\GG$, endowed with the $\HH$-perimeter measure.

We give a necessary and sufficient condition for $k$-step nilmanifolds associated with graphs $(k \geq 3)$ to admit Anosov automorphisms. We also prove nonexistence of Anosov automorphisms on certain classes of 2-step and 3-step nilmanifolds.

Estimating sparse transition matrix from partially observed high-dimensional time series data.

Study proposes an active subsampling method for estimating individualized thresholds in high-dimensional data.

New near-metrics capture similarity for diverse data types.

Estimates transition rates of continuous-time Markov chains using imprecise probabilistic methods.

New approach to analyze matrix denoising using gradient flow and fixed point equations.

In recent years, non-parametric methods utilizing random walks on graphs have been used to solve a wide range of machine learning problems, but in their simplest form they do not scale well due to the quadratic complexity. In this paper, a new dual-tree based variational approach for approximating the transition matrix…

The paper studies algebraic relations of first integrals on specific Lie groups.

We apply the Nash-Moser theorem for exact sequences of R. Hamilton to the context of deformations of Lie algebras and we discuss some aspects of the scope of this theorem in connection with the polynomial ideal associated to the variety of nilpotent Lie algebras. This allows us to introduce the space $H_{k-nil}^2(\math…

Study of correlated Wigner matrices with BBP transitions.

Study transitions between tableau and spider bases for Specht modules.

Paper proposes Masking for robust classifier learning from noisy labels.

Let G be a k-step Carnot group. We prove an isoperimetric-type inequality for compact C^2-smooth immersed hypersurfaces with boundary, involving the horizontal mean curvature of the hypersurface. This generalizes an inequality due to Michael and Simon, and Allard, independently. Some applications are discussed.

TMTF improves time series visualization by separating dynamic regimes.

Method determines credit transition matrix from cumulative default probabilities.

The latent Dirichlet allocation (LDA) model is a widely-used latent variable model in machine learning for text analysis. Inference for this model typically involves a single-site collapsed Gibbs sampling step for latent variables associated with observations. The efficiency of the sampling is critical to the success o…

Optimal spectral method found for inhomogeneous spiked Wigner model.

Graph diffusion processes approximate manifold heat semigroups using graph transition matrices.

A new model reduces rating transition matrix estimation errors for small portfolios.

Improves detection of low-rank signals from noisy data matrices.

SC-InfoNCE improves InfoNCE for feature clustering in contrastive learning.

Lecture notes on non-Kähler complex threefolds, focusing on conifold transitions.

Let $M$ be a complete Riemannian metric of sectional curvature within $[-a^2,-1]$ whose fundamental group contains a $k$-step nilpotent subgroup of finite index. We prove that $a\ge k$ answering a question of M. Gromov. Furthermore, we show that for any $ε>0$, the manifold $M$ admits a complete Riemannian metric of sec…

TOLD++ improves convergence of diffusion models by critically damping the forward transition matrix.

Study on eigenvalue distribution of correlated time series deforming the semi-circle law.

Study on estimating sparse transition matrix of partially-observed VAR with noisy and sparse data.

Study on signal-plus-noise decomposition in nonlinear spiked random matrices.

Gradient descent solves rank-one matrix estimation problem with detailed time evolution analysis.

Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an entire batch of examples at once, for example, when labels can be acquired in para…

Polynomial-time algorithm learns latent-state systems without spectral radius assumptions.

Study quantifies performance gap between tensor and matrix-based approaches in nested matrix-tensor model.

Characterizes RFF regression in large $n,p,N$ setting, providing precise learning phases and double descent curve.

Investment diversification affects financial stability, depending on network connectivity.

Paper tackles matrix estimation under arbitrary noise, achieving minimax optimality.