arXiv research

New theory for local parameterization of deep ReLU networks.

Local method identifies causal relations in Markov equivalent DAGs.

Identifies Lorentzian locally symmetric spaces where Calabi operator suffices to determine Killing operator range.

LOAD discovers optimal adjustments locally for scalable causal inference.

New proof shows how to identify DAGs with weakly increasing errors.

New methods identify local clusters in graphs with few labels.

We identify direct causes of a target variable from observational data without full DAG identifiability.

Proposes a method to identify causal relationships using background knowledge.

New method identifies important features and interactions in RF models.

We study the theoretical properties of learning a dictionary from $N$ signals $\mathbf x_i\in \mathbb R^K$ for $i=1,...,N$ via $l_1$-minimization. We assume that $\mathbf x_i$'s are $i.i.d.$ random linear combinations of the $K$ columns from a complete (i.e., square and invertible) reference dictionary $\mathbf D_0 \in…

Axis-aligned subspace clustering generally entails searching through enormous numbers of subspaces (feature combinations) and evaluation of cluster quality within each subspace. In this paper, we tackle the problem of identifying subsets of features with the most significant contribution to the formation of the local n…

b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.

We study the quasi-convergence equivalence of some families of metrics on locally homogeneous closed 4-manifolds with trivial isotropy group, and identify the dimension of each equivalence class under certain conditions.

funLOCI identifies clusters in functional data.

Bayesian framework for identifying localized regions of interest in dynamical systems.

Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-bas…

Extends Calabi operator to Riemannian locally symmetric spaces.

Study local exploration on dynamic graphs with time-varying edges.

We propose an inlier-based outlier detection method capable of both identifying the outliers and explaining why they are outliers, by identifying the outlier-specific features. Specifically, we employ an inlier-based outlier detection criterion, which uses the ratio of inlier and test probability densities as a measure…

Physical systems are modelled and investigated within simulation software in an increasing range of applications. In reality an investigation of the system is often performed by empirical test scenarios which are related to typical situations. Our aim is to derive a method which generates diverse test scenarios each re…

Study identifies subvarieties of projective varieties mapping to models.

We consider online detection strategies for identifying a change point in a stream of quantum particles allegedly prepared in identical states. We show that the identification of the change point can be done without error via sequential local measurements while attaining the optimal performance bound set by quantum mec…

3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to captu…

CutMix training technique improves spatial locality in Vision Transformers.

Improved learning of probabilistic box embeddings by modeling parameters with Gumbel distributions.

This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing mode…

Study reveals structure of local minima in GMMs, identifying key cluster centers.

Formula for sections on complex manifolds with non-isolated components.

Logifold improves ensemble machine learning by identifying fuzzy domains.

DAGnosis uses DAGs to identify and localize data inconsistencies.

Neural networks can learn relationships that traditional models cannot.

We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous path on which the cross-entropy loss is non-increasing and gets arbitrarily clos…

Equivariant localization techniques give a rigorous interpretation of the Witten genus as an integral over the double loop space. This provides a geometric explanation for its modularity properties. It also reveals an interplay between the geometry of double loop spaces and complex analytic elliptic cohomology. In part…

A motif-based framework identifies local spillover structures in financial markets.

Develops a method to interpret deep learning models by identifying key features.

We consider random walks on locally compact groups, extending the geometric criteria for the identification of their Poisson boundary previously known for discrete groups. First, we prove a version of the Shannon-McMillan-Breiman theorem, which we then use to generalize Kaimanovich's ray approximation and strip approxi…

Locally symplectic structure found on Kerr space-time.

RelatIF selects more intuitive training examples for explaining model predictions.

We identify higher-charge configurations that satisfy Euler-Lagrange equations for the (strong coupling limit of) Faddeev-Hopf model, by means of adequate changes of the domain metric and a reduction technique based on $α$-Hopf construction. In the last case it is proved that the solutions are local minima for the redu…

We study strict local martingales via h-transforms, a method which first appeared in Delbaen-Schachermayer. We show that strict local martingales arise whenever there is a consistent family of change of measures where the two measures are not equivalent to one another. Several old and new strict local martingales are i…

It is common for CCTV operators to overlook inter- esting events taking place within the crowd due to large number of people in the crowded scene (i.e. marathon, rally). Thus, there is a dire need to automate the detection of salient crowd regions acquiring immediate attention for a more effective and proactive surveil…

Local learning method selects covariates for causal effect estimation in the presence of latent variables.

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…

We consider locally conformal Kaehler geometry as an equivariant, homothetic Kaehler geometry (K,Γ). We show that the de Rham class of the Lee form can be naturally identified with the homomorphism projecting Γto its dilation factors, thus completing the description of locally conformal Kaehler geometry in this equivar…

We identify the 2-groupoid of deformations of a gerbe on a smooth manifold with the Deligne 2-groupoid of a corresponding twist of the DGLA of local Hochschild cochains on infinite jets of smooth functions.

Improved local feature attributions using neighbourhood reference distributions.

New method removes interference bias in causal models.

New algorithm identifies causal effects in latent confounding models.