Suppose that one particular block in a stochastic block model is of interest, but block labels are only observed for a few of the vertices in the network. Utilizing a graph realized from the model and the observed block labels, the vertex nomination task is to order the vertices with unobserved block labels into a rank…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “canonical labels”
Graph alignment in two correlated random graphs refers to the task of identifying the correspondence between vertex sets of the graphs. Recent results have characterized the exact information-theoretic threshold for graph alignment in correlated Erdős-Rényi graphs. However, very little is known about the existence of e…
GraphGen generates large labeled graphs efficiently and accurately.
problem Scalability and comprehensive evaluation of graph generation techniques.
method Converts graphs to sequences using minimum DFS codes and learns joint distributions with an LSTM.
result Significantly faster and better quality than state-of-the-art techniques.
End-to-end deep learning for multi-view clustering improves accuracy across various data types.
problem Limited multi-view clustering methods for general data types and suboptimal two-stage process.
method Permutation-based canonical correlation objective for fused representations; pseudo-labels for clustering; theoretical error bound.
result Proposed model provides meaningful fused representations and effective clustering across multiple views.
Multi-view learning (MVL) is a strategy for fusing data from different sources or subsets. Canonical correlation analysis (CCA) is very important in MVL, whose main idea is to map data from different views onto a common space with maximum correlation. Traditional CCA can only be used to calculate the linear correlation…
In this paper we study an analog of minimal surfaces called Weyl-minimal surfaces in conformal manifolds with a Weyl connection . We show that there is an Eells-Salamon type correspondence between nonvertical -holomorphic curves in the weightless twistor space and branched Weyl-minimal surfaces.…
Efficient algorithm for CCA on Riemannian manifolds with fast convergence.
problem Efficiently computing canonical correlation components on Riemannian manifolds.
method Reparametrization of projection matrices for stochastic optimization on Riemannian manifolds.
result Achieves $O( rac{1}{t})$ convergence rate for top components with runtime complexity.
New method uses unlabeled data to improve generalization bounds for deep learning.
problem Vacuous guarantees and shrinking holdout sets for overparameterized models.
method Augmenting labeled training set with unlabeled data and training as usual.
result Proves tight upper bounds on true risk for 0-1 empirical risk minimization.
Proposes a new calibration error estimator for deep neural networks.
problem Improves calibration of deep neural networks, especially for canonical calibration.
method Uses a Dirichlet kernel density estimate to create a low-bias, trainable calibration error estimator.
result Asymptotically converges to true calibration error, enabling efficient estimation and mini-batch updates.
Let be a simplicial complex with a piecewise linear function . The Reeb graph is the quotient of , where we collapse each connected component of to a single point. Let the nodes of be all homologically critical points where any homology of the corresponding c…
Given a graded -module over an -algebra in spaces, we construct an augmented semi-simplicial space up to higher coherent homotopy over it, called its canonical resolution, whose graded connectivity yields homological stability for the graded pieces of the module with respect to constant and abelian coefficien…
New algorithms detect communities in sparse graphs with labeled data.
problem Detecting communities in sparse graphs with limited labeled data.
method Introduces two algorithms: combinatorial and optimization-based, to integrate labeled data with graph structures.
result Detection of communities is feasible throughout the parameter domain with arbitrary labeled data.
New method uses limited labeled data and multiple starts to adapt models across domains.
problem Accurate predictions in target domain with few labeled data.
method Fine-tuning from multiple adaptive starts, extending UDA methods.
result Minimax-optimal target performance with limited labeled target data.
Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding. In this …
Study shows harmful overfitting in Sobolev spaces even as training data grows.
problem Harmful overfitting in Sobolev spaces under noisy conditions.
method Geometric argument using Sobolev inequalities.
result Approximately norm-minimizing interpolators exhibit harmful overfitting.
This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phra…
Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networkscs.LG
The effectiveness of biosignal generation and data augmentation with biosignal generative models based on generative adversarial networks (GANs), which are a type of deep learning technique, was demonstrated in our previous paper. GAN-based generative models only learn the projection between a random distribution as in…
The purpose of this paper is twofold. On one hand, we introduce a modification of the dual canonical basis for invariant tensors of the 3-dimensional irreducible representation of , given in terms of Jacobi diagrams, a central tool in quantum topology. On the other hand, we use this modified basis to study t…
This research improves representation learning for new domains with limited new supervision.
problem Learning representations that generalize well to new domains with minimal new data.
method Encourages linearity of factors of variation through learned linear transformations called latent canonicalizers.
result Reduces the number of observations needed to generalize to a similar target domain compared to supervised baselines.
We show that the Kahler-Ricci flow on an algebraic manifold of positive Kodaira dimension and semi-ample canonical line bundle converges to a unique canonical metric on its canonical model. It is also shown that there exists a canonical measure of analytic Zariski decomposition on an algebraic manifold of positive Koda…
A new method learns meaningful distances between samples using optimal transport.
problem Learning meaningful distances between samples in datasets without labeled data.
method Computes OT distances between samples and features using singular vectors of a function mapping ground metrics to OT distances.
result Wasserstein Singular Vectors provide a scalable solution for unsupervised ground metric learning.
In this article we construct a canonical Kähler-Einstein current on a LC (log canonical) pairs of log general type as the limit of a sequence of canonical Kähler-Einstein currents on KLT(Kawamata log terminal) pairs of log general type. We call the volume form associated with the canonical Kähler-Einstein current the c…
New Hamiltonian Monte Carlo method for non-canonical dynamics.
problem Incompatibility of canonical symplectic structure with non-canonical dynamics.
method Developed a framework for Hamiltonian Monte Carlo using non-canonical symplectic structures with implicit integration.
result Non-canonical Hamiltonian Monte Carlo provides sampling advantages.
We propose an efficient algorithm for solving orthogonal canonical correlation analysis (OCCA) in the form of trace-fractional structure and orthogonal linear projections. Even though orthogonality has been widely used and proved to be a useful criterion for pattern recognition and feature extraction, existing methods …
Pair-Wise Cluster Analysisstat.ML
This paper studies the problem of learning clusters which are consistently present in different (continuously valued) representations of observed data. Our setup differs slightly from the standard approach of (co-) clustering as we use the fact that some form of `labeling' becomes available in this setup: a cluster is …
The paper finds canonical triangulations for specific 3-manifolds.
problem Finding canonical decompositions for cusped hyperbolic 3-manifolds.
method Showed local convexity at every face of the geometric triangulation.
result Found canonical triangulations for Dehn fillings of the Borromean rings link complement and related manifolds.
We identify a strong equivalence between neural network based machine learning (ML) methods and the formulation of statistical data assimilation (DA), known to be a problem in statistical physics. DA, as used widely in physical and biological sciences, systematically transfers information in observations to a model of …
Improved linear regression with privacy and robustness guarantees.
problem Private and robust linear regression with adversarial corruption.
method Differentially private stochastic gradient descent with full-batch gradient descent and adaptive clipping.
result Near optimal sample complexity for both private and robust linear regression.
The paper defines and studies canonical parameters on surfaces in 4D space.
problem Understanding surfaces in 4D space without minimal points.
method Defining and proving existence of canonical principal parameters.
result Surfaces in 4D space are uniquely determined by four functions satisfying partial differential equations.
Counterexample disproves log canonical Beauville--Bogomolov decomposition.
problem Disproving the log canonical Beauville--Bogomolov decomposition.
method Constructing a specific log canonical, K-trivial variety with non-birational fibers.
result Provides a counterexample to the Beauville--Bogomolov decomposition in the log canonical setting.
For a submanifold M in a Euclidean space, the tangential component x^T of the position vector field x of M is the most natural vector field tangent to the Euclidean submanifold, called the canonical vector field of M. In this article, first we prove that the canonical vector field of every Euclidean submanifold is alwa…
Canonical correlation analysis was proposed by Hotelling [6] and it measures linear relationship between two multidimensional variables. In high dimensional setting, the classical canonical correlation analysis breaks down. We propose a sparse canonical correlation analysis by adding l1 constraints on the canonical vec…
This paper rethinks confidence calibration under covariate shifts.
problem Calibration methods struggle with covariate shifts and unstable importance weighting.
method Derives Expectation consistency condition and proposes Expectation consistency loss (ECL).
result ECL loss is compatible with various types of calibration and has the same sample complexity as ECE.
Paper classifies compact symmetric triads using double Satake diagrams and canonical forms.
problem Classifying compact symmetric triads.
method Introducing double Satake diagrams and canonical forms, proving their existence and properties.
result Existence and properties of canonical forms for compact simple symmetric triads.
Canonical connections and algebraic Wanas solitons of three-dimensional Lorentzian Lie groupsmath.DG
The paper classifies solitons on specific Lie groups.
problem Classifying solitons on three-dimensional Lorentzian Lie groups.
method Computing Wanas tensor and defining algebraic Wanas solitons.
result Classification of algebraic Wanas solitons on specific Lie groups.
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use of class labels. Recent CCA methods have started to address this weakness but are limited in that they do not simultaneously optimize the CC…
The covariant canonical formalism is a covariant extension of the traditional canonical formalism of fields. In contrast to the traditional canonical theory, it has a remarkable feature that canonical equations of gauge theories or gravity are not only manifestly Lorentz covariant but also gauge covariant or diffeomorp…
Study orders of canonical bundles over graph configuration spaces.
problem Determining bundle orders for planar and nonplanar graphs.
method Analyzing configuration spaces of graphs to find bundle orders.
result Bundle orders are 2 for planar and 4 for nonplanar graphs.
Using the fact that any minimal strongly regular surface carries locally canonical principal parameters, we obtain a canonical representation of these surfaces, which makes more precise the Weierstrass representation in canonical principal parameters. This allows us to describe locally the solutions of the natural part…
In this paper many classes of sets of matrices with entries in F (F=R, F=C, F=H) are introduced. Each class with the corresponding topology determines a real analytical, complex or symplectic manifold for F=R, F=C or F=H respectively. Any such family is called to be a set of canonical forms of matrices. The constructio…
Introduces a new canonical connection for Riemannian manifolds and proves Frobenius theorem geometrically.
problem Geometric proof of the Frobenius theorem on Riemannian manifolds.
method Introduces a new canonical connection and applies it to prove the Frobenius theorem.
result Geometric proof of the Frobenius theorem.
Canonical connections and algebraic Ricci solitons of three-dimensional Lorentzian Lie groupsmath.DG
The paper classifies Ricci solitons on specific Lorentzian Lie groups.
problem Classifying algebraic Ricci solitons on three-dimensional Lorentzian Lie groups.
method Computed canonical and Kobayashi-Nomizu connections and their curvatures; defined algebraic Ricci solitons.
result Classified algebraic Ricci solitons on specific Lorentzian Lie groups.
Explains BV Laplacian on half-densities in simple terms.
problem None explicitly stated; focuses on explanation.
method Didactical review of BV Laplacian on half-densities.
result Explains BV Laplacian concept in plain language.
Study complex solvmanifolds with trivial canonical bundle and hypercomplex geometry.
problem Characterize and produce examples of complex solvmanifolds with trivial canonical bundle.
method Characterize invariant trivializing sections using Koszul 1-form, provide algebraic obstructions, and exhibit specific examples.
result New examples of complex solvmanifolds with trivial canonical bundle and algebraic obstructions for triviality.
Characterizes uncertainty in high-dimensional linear classification models.
problem Assessing uncertainty in high-dimensional linear classification models.
method Approximate message passing algorithm for posterior marginals, closed-form formula for joint statistics.
result Closed-form formula for joint statistics between logistic classifier, Bayesian uncertainty, and ground-truth probit uncertainty.
In this article, we construct the canonical semipositive current or the canonical measure ( the potential of the canonical semipositive current) on a smooth projective variety of nonnegative Kodaira dimension in terms of a dynamical system of Bergman kernels. This current is considered to be a generalization of a Kä…
Trajectory-level supervision allows efficient offline reinforcement learning.
problem Offline reinforcement learning
method Developing a statistical theory for offline policy optimization from trajectory-level labels
result Proving a high-probability guarantee of order
Canonical correlation analysis is a family of multivariate statistical methods for the analysis of paired sets of variables. Since its proposition, canonical correlation analysis has for instance been extended to extract relations between two sets of variables when the sample size is insufficient in relation to the dat…