Browsing by Subject "cs.LG"
Now showing items 120 of 25

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
This paper concerns the a priori generalization analysis of the Deep Ritz Method (DRM) [W. E and B. Yu, 2017], a popular neuralnetworkbased method for solving high dimensional partial differential equations. We derive ... 
A stochastic version of Stein Variational Gradient Descent for efficient sampling
We propose in this work RBMSVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference. The method is to apply ... 
Adaptive Hyperbox Matching for Interpretable Individualized Treatment Effect Estimation.
(CoRR, 2020)We propose a matching method for observational data that matches units with others in unitspecific, hyperboxshaped regions of the covariate space. These regions are large enough that many matches are created for each ... 
Approximation of Functions over Manifolds: A Moving LeastSquares Approach
We present an algorithm for approximating a function defined over a $d$dimensional manifold utilizing only noisy function values at locations sampled from the manifold with noise. To produce the approximation we do not require ... 
ButterflyNet: Optimal Function Representation Based on Convolutional Neural Networks
Deep networks, especially Convolutional Neural Networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. ... 
Complexity of zigzag sampling algorithm for strongly logconcave distributions
We study the computational complexity of zigzag sampling algorithm for strongly logconcave distributions. The zigzag process has the advantage of not requiring time discretization for implementation, and that each ... 
CrossDomain Multitask Learning with Latent Probit Models
Learning multiple tasks across heterogeneous domains is a challenging problem since the feature space may not be the same for different tasks. We assume the data in multiple tasks are generated from a latent common domain ... 
dameflame: A Python Library Providing Fast Interpretable Matching for Causal Inference.
(CoRR, 2021)dameflame is a Python package for performing matching for observational causal inference on datasets containing discrete covariates. This package implements the Dynamic Almost Matching Exactly (DAME) and Fast LargeScale Almost ... 
DCFNet: Deep Neural Network with Decomposed Convolutional Filters
(35th International Conference on Machine Learning, ICML 2018, 20180101)©35th International Conference on Machine Learning, ICML 2018.All Rights Reserved. Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest ... 
Expression of Fractals Through Neural Network Functions
To help understand the underlying mechanisms of neural networks (NNs), several groups have, in recent years, studied the number of linear regions $\ell$ of piecewise linear functions generated by deep neural networks (DNN). In ... 
Global optimality of softmax policy gradient with single hidden layer neural networks in the meanfield regime
We study the problem of policy optimization for infinitehorizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate ... 
Hölder Bounds for Sensitivity Analysis in Causal Reasoning.
(CoRR, 2021)We examine interval estimation of the effect of a treatment T on an outcome Y given the existence of an unobserved confounder U. Using H\"older's inequality, we derive a set of bounds on the confounding bias E[YT=t]E[... 
Inferring Latent Structure From Mixed Real and Categorical Relational Data
We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each ... 
Machine Learning to Predict Developmental Neurotoxicity with Highthroughput Data from 2D Bioengineered Tissues
There is a growing need for fast and accurate methods for testing developmental neurotoxicity across several chemical exposure sources. Current approaches, such as in vivo animal studies, and assays of animal and human primary ... 
Malignancy Prediction and Lesion Identification from Clinical Dermatological Images.
(CoRR, 2021)We consider machinelearningbased malignancy prediction and lesion identification from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture. Additionally, we do not assume that ... 
Manifold Approximation by Moving LeastSquares Projection (MMLS)
In order to avoid the curse of dimensionality, frequently encountered in Big Data analysis, there was a vast development in the field of linear and nonlinear dimension reduction techniques in recent years. These ... 
On the Universality of Rotation Equivariant Point Cloud Networks.
(CoRR, 2020)Learning functions on point clouds has applications in many fields, including computer vision, computer graphics, physics, and chemistry. Recently, there has been a growing interest in neural architectures that are invariant ... 
PrivacyPreserving Collaborative Prediction using Random Forests
We study the problem of privacypreserving machine learning (PPML) for ensemble methods, focusing our effort on random forests. In collaborative analysis, PPML attempts to solve the conflict between the need for data sharing and ... 
RotDCF: Decomposition of Convolutional Filters for RotationEquivariant Deep Networks.
(CoRR, 2018)Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper proposes ... 
Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA
We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the highdimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression ...