Search Results for author:
Found 36 papers, 20 papers with code
Exponential weight averaging as damped harmonic motion
The exponential moving average (EMA) is a commonly used statistic for providing stable estimates of stochastic quantities in deep learning optimization.
Multi-modal Differentiable Unsupervised Feature Selection
Multi-modal high throughput biological data presents a great scientific opportunity and a significant computational challenge.
Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation
We introduce a simple modification to the standard maximum likelihood estimation (MLE) framework.
ManiFeSt: Manifold-based Feature Selection for Small Data Sets
This in turn allows for the extraction of the hidden manifold underlying the features and avoids overfitting, facilitating few-sample FS.
Neural Inverse Transform Sampler
Any explicit functional representation $f$ of a density is hampered by two main obstacles when we wish to use it as a generative model: designing $f$ so that sampling is fast, and estimating $Z = \int f$ so that $Z^{-1}f$ integrates to 1.
Hyperbolic Procrustes Analysis Using Riemannian Geometry
Here, we take a purely geometric approach for label-free alignment of hierarchical datasets and introduce hyperbolic Procrustes analysis (HPA).
Exploiting 3D Shape Bias towards Robust Vision
To tackle the problem from a new perspective, we encourage closer collaboration between the robustness and 3D vision communities.
Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features
Experimenting on several real-world datasets, we demonstrate that our proposed approach outperforms similar approaches designed to avoid only correlated or nuisance features, but not both.
Probabilistic Robust Autoencoders for Outlier Detection
We first present the Robust AutoEncoder (RAE) objective as a minimization problem for splitting the data into inliers and outliers.
Geon3D: Exploiting 3D Shape Bias towards Building Robust Machine Vision
To tackle the problem from a new perspective, we encourage closer collaboration between the robustness and 3D vision communities.
L0-Sparse Canonical Correlation Analysis
We further propose $\ell_0$-Deep CCA for solving the problem of non-linear sparse CCA by modeling the correlated representations using deep nets.
Locally Sparse Neural Networks for Tabular Biomedical Data
By forcing the model to select a subset of the most informative features for each sample, we reduce model overfitting in low-sample-size data and obtain an interpretable model.
Spectral Top-Down Recovery of Latent Tree Models
For large trees, a common approach, termed divide-and-conquer, is to recover the tree structure in two steps.
$\ell_0$-based Sparse Canonical Correlation Analysis
We further propose $\ell_0$-Deep CCA for solving the problem of non-linear sparse CCA by modeling the correlated representations using deep nets.
Deep Gated Canonical Correlation Analysis
The proposed procedure learns two non-linear transformations and simultaneously gates the input variables to identify a subset of most correlated variables.
Differentiable Unsupervised Feature Selection based on a Gated Laplacian
In this paper, we present a method for unsupervised feature selection, and we demonstrate its use for the task of clustering.
Doubly-Stochastic Normalization of the Gaussian Kernel is Robust to Heteroskedastic Noise
When the data points reside in Euclidean space, a widespread approach is to from an affinity matrix by the Gaussian kernel with pairwise distances, and to follow with a certain normalization (e. g. the row-stochastic normalization or its symmetric variant).
Spectral neighbor joining for reconstruction of latent tree models
A common assumption in multiple scientific applications is that the distribution of observed data can be modeled by a latent tree graphical model.
The Spectral Underpinning of word2vec
word2vec due to Mikolov \textit{et al.} (2013) is a word embedding method that is widely used in natural language processing.
Heavy-tailed kernels reveal a finer cluster structure in t-SNE visualisations
T-distributed stochastic neighbour embedding (t-SNE) is a widely used data visualisation technique.
Feature Selection using Stochastic Gates
Feature selection problems have been extensively studied for linear estimation, for instance, Lasso, but less emphasis has been placed on feature selection for non-linear functions.
Defending against Adversarial Images using Basis Functions Transformations
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images.
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
Latent variable models with hidden binary units appear in various applications.
SpectralNet: Spectral Clustering using Deep Neural Networks
Moreover, the map learned by SpectralNet naturally generalizes the spectral embedding to unseen data points.
Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding
t-distributed Stochastic Neighborhood Embedding (t-SNE) is a method for dimensionality reduction and visualization that has become widely popular in recent years.
Randomized Near Neighbor Graphs, Giant Components, and Applications in Data Science
If we pick $n$ random points uniformly in $[0, 1]^d$ and connect each point to its $k-$nearest neighbors, then it is well known that there exists a giant connected component with high probability.
Data-Driven Tree Transforms and Metrics
Often the data is such that the observations do not reside on a regular grid, and the given order of the features is arbitrary and does not convey a notion of locality.
Mahalanonbis Distance Informed by Clustering
Specifically we show that organizing similar coordinates in clusters can be exploited for the construction of the Mahalanobis distance between samples.
Unsupervised Ensemble Regression
Consider a regression problem where there is no labeled data and the only observations are the predictions $f_i(x_j)$ of $m$ experts $f_{i}$ over many samples $x_j$.
Removal of Batch Effects using Distribution-Matching Residual Networks
We apply our method to mass cytometry and single-cell RNA-seq datasets, and demonstrate that it effectively attenuates batch effects.
DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network
We introduce DeepSurv, a Cox proportional hazards deep neural network and state-of-the-art survival method for modeling interactions between a patient's covariates and treatment effectiveness in order to provide personalized treatment recommendations.
A Deep Learning Approach to Unsupervised Ensemble Learning
We show how deep learning methods can be applied in the context of crowdsourcing and unsupervised ensemble learning.
Unsupervised Ensemble Learning with Dependent Classifiers
In unsupervised ensemble learning, one obtains predictions from multiple sources or classifiers, yet without knowing the reliability and expertise of each source, and with no labeled data to assess it.
Estimating the Accuracies of Multiple Classifiers Without Labeled Data
In various situations one is given only the predictions of multiple classifiers over a large unlabeled test data.
Ranking and combining multiple predictors without labeled data
This scenario is different from the standard supervised setting, where each classifier accuracy can be assessed using available labeled data, and raises two questions: given only the predictions of several classifiers over a large set of unlabeled test data, is it possible to a) reliably rank them; and b) construct a meta-classifier more accurate than most classifiers in the ensemble?
TrAp: a Tree Approach for Fingerprinting Subclonal Tumor Composition
Herein we propose a framework for deconvolving data from a single genome-wide experiment to infer the composition, abundance and evolutionary paths of the underlying cell subpopulations of a tumor.
