arXiv research

Improves performance in various machine learning tasks by reparameterizing subset sampling.

This paper uses deep neural networks for one-class classification by splitting normal data into typical and atypical subsets.

This paper reduces graph-Laplacian dimensionality for spectral clustering of subsets.

The paper shows how to avoid the trivial representation in IB by choosing the right β.

All projections of typical Cantor sets in high dimensions are Cantor sets.

Proposes a differentiable hypergeometric distribution for learning group importance.

Link prediction in networks is typically accomplished by estimating or ranking the probabilities of edges for all pairs of nodes. In practice, especially for social networks, the data are often collected by egocentric sampling, which means selecting a subset of nodes and recording all of their edges. This sampling mech…

Inspired by work of Borzellino and Brunsden, we generalize the notion of a submanifold identifying a natural and sufficiently general condition which guarantees that a subset of an (effective) orbifold carries itself a canonical induced orbifold structure. We illustrate the strength of this approach generalizing typica…

We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one impo…

The paper introduces a framework to select efficient datasets for preserving model rankings.

A method for finding most influential sets reduces a complex problem to a sequence of simpler top-$k$ problems.

New method for evaluating and learning in complex decision-making scenarios.

New method predicts unobserved interactions between sets of elements.

PixelCNN models can achieve state-of-the-art results on CIFAR-10 with exact likelihood computation.

New method learns transport cost from subset correspondence.

Paper introduces template functions for featurizing persistence diagrams.

Tab-Shapley identifies top-k anomalies in tabular data quality insights.

Nested dichotomies for multiclass tasks often fail to calibrate probabilities.

Parallel decoding improves machine translation efficiency and accuracy.

Many key algorithms in 3-manifold topology involve the enumeration of normal surfaces, which is based upon the double description method for finding the vertices of a convex polytope. Typically we are only interested in a small subset of these vertices, thus opening the way for substantial optimization. Here we give an…

We consider a compact, star-shaped, mean convex hypersurface $Σ^2\subset \mathbb{R}^3$. We prove that in some cases the flow exists until it shrinks to a point in a spherical manner, which is very typical for convex surfaces as well (see \cite{An1}). We also prove that in the case we have a surface of revolution which …

New criteria for Cantor set tameness and wildness via projections.

Safe-DRFS selects features robust to covariate shifts for reliable performance.

DUA-D2C refines D2C for better deep learning generalization.

DART optimizes subset selection in non-linear bandit problems.

ModHiFi identifies critical components for model modification without gradients or loss function.

This paper improves fraud prevention rule sets in fintech by generating diverse rules and finding Pareto-optimal subsets.

Optimizes MCMC output compression by selecting a subset of states.

CNNs overinterpret inputs, leading to high accuracy without meaningful features.

DiPriMe forests use private medians to create balanced tree splits for privacy-protected data.

New algorithm scales NDPP learning and inference to large item collections.

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing b…

Optimal experiments tighten causal effect bounds efficiently.

Bayesian optimization (BO) is a global optimization strategy designed to find the minimum of an expensive black-box function, typically defined on a compact subset of $\mathcal{R}^d$, by using a Gaussian process (GP) as a surrogate model for the objective. Although currently available acquisition functions address this…

Develops method to train classifiers on incomplete feature datasets.

We consider learning a causal ordering of variables in a linear non-Gaussian acyclic model called LiNGAM. Several existing methods have been shown to consistently estimate a causal ordering assuming that all the model assumptions are correct. But, the estimation results could be distorted if some assumptions actually a…

Solves portfolio optimization with cardinality constraints using column generation.

Feature selection is an important task in many problems occurring in pattern recognition, bioinformatics, machine learning and data mining applications. The feature selection approach enables us to reduce the computation burden and the falling accuracy effect of dealing with huge number of features in typical learning …

The easy access to large data sets has allowed for leveraging methodology in network physics and complexity science to disentangle patterns and processes directly from the data, leading to key insights in the behavior of systems. Here we use to country specific food production data to study binary and weighted topologi…

A new feature selection method using attention for neural networks.

Decision forests, including Random Forests and Gradient Boosting Trees, have recently demonstrated state-of-the-art performance in a variety of machine learning settings. Decision forests are typically ensembles of axis-aligned decision trees; that is, trees that split only along feature dimensions. In contrast, many r…

A new framework for time series analysis using state-space learning.

We prove a rigidity theorem that shows that, under many circumstances, quasi-isometric embeddings of equal rank, higher rank symmetric spaces are close to isometric embeddings. We also produce some surprising examples of quasi-isometric embeddings of higher rank symmetric spaces. In particular, we produce embeddings of…

An explicit classification of simply connected compact homogeneous CR manifolds G/L of codimension one, with non-degenerate Levi form, is given. There are three classes of such manifolds: a) the standard CR homogeneous manifolds which are homogeneous S^1-bundles over a flag manifold F, with CR structure induced by an i…

New rationalization method avoids spurious correlations.

Crowdsourcing provides a popular paradigm for data collection at scale. We study the problem of selecting subsets of workers from a given worker pool to maximize the accuracy under a budget constraint. One natural question is whether we should hire as many workers as the budget allows, or restrict on a small number of …

Paper proposes efficient online estimation of causal effects by deciding which data sources to query.

New method estimates sparse covariance matrices in logit mixtures.