arXiv research

Framework improves ML flood mapping generalization.

Generative model uses random convolutional features to create financial time series.

Proposes a new method to prevent overfitting in deep neural networks.

This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible learning for generating and learning latent features using the network itself. By generating latent features corresponding to hard samples an…

Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning. While saliency maps may help identify relevant features (e.g., p…

Lower bound proves ridgeless regression performs poorly near interpolation threshold.

ERM performs well in feature learning with minimal feature maps.

We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.

New feature mapping approach improves recommendation accuracy and explainability.

The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…

CAM-GAN improves GANs for continual learning with efficient feature map transformations.

Random feature maps improve forecasting with cheaper computation.

Random feature maps are ubiquitous in modern statistical machine learning, where they generalize random projections by means of powerful, yet often difficult to analyze nonlinear operators. In this paper, we leverage the "concentration" phenomenon induced by random matrix theory to perform a spectral analysis on the Gr…

Paper proposes an efficient RL algorithm for discounted MDPs using feature mapping.

Kernel approximation using randomized feature maps has recently gained a lot of interest. In this work, we identify that previous approaches for polynomial kernel approximation create maps that are rank deficient, and therefore do not utilize the capacity of the projected feature space effectively. To address this chal…

Quantum machine learning models can approximate any continuous function.

Proposes MGPLL for PL learning with non-random noise.

New random feature maps for Laplacian and related kernels.

New method learns disentangled representations using Gromov-Monge maps.

Markov blanket feature selection, while theoretically optimal, is generally challenging to implement. This is due to the shortcomings of existing approaches to conditional independence (CI) testing, which tend to struggle either with the curse of dimensionality or computational complexity. We propose a novel two-step a…

Neural networks can separate non-separable data using feature maps.

We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks represent fields on a homogeneous base space, and layers are equivariant maps between spaces of fields. The theory enables a systematic cla…

ICAM creates interpretable feature attribution maps for brain images.

Paper generalizes teacher-student model for realistic data.

Random feature maps improve forecasting of chaotic dynamical systems.

Max-margin classifiers' behavior is studied in high dimensions with non-Gaussian features.

This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.

Many practical machine learning tasks employ very deep convolutional neural networks. Such large depths pose formidable computational challenges in training and operating the network. It is therefore important to understand how fast the energy contained in the propagated signals (a.k.a. feature maps) decays across laye…

We introduce a new discriminant analysis method (Empirical Discriminant Analysis or EDA) for binary classification in machine learning. Given a dataset of feature vectors, this method defines an empirical feature map transforming the training and test data into new data with components having Gaussian empirical distrib…

Non-linear kernel methods can be approximated by fast linear ones using suitable explicit feature maps allowing their application to large scale problems. We investigate how convolution kernels for structured data are composed from base kernels and construct corresponding feature maps. On this basis we propose exact an…

Random feature model approximates PDE solutions efficiently.

A new Gaussian process framework uses neural feature maps for scalable, accurate inference.

Improved disentanglement in VAEs using aggregated feature maps.

Recent years have demonstrated that using random feature maps can significantly decrease the training and testing times of kernel-based algorithms without significantly lowering their accuracy. Regrettably, because random features are target-agnostic, typically thousands of such features are necessary to achieve accept…

Deep neural features identify unique vehicles from dash-cam feeds.

Improves machine learning models by incorporating physical laws into feature maps.

Kernel approximation methods create explicit, low-dimensional kernel feature maps to deal with the high computational and memory complexity of standard techniques. This work studies a supervised kernel learning methodology to optimize such mappings. We utilize the Discriminant Information criterion, a measure of class …

Improved disentanglement through learned feature aggregation.

Featurization improves density ratio estimation for complex data.

Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity …

No-collision maps improve manifold learning for image data.

Characterizes test error in learning with deep, structured feature maps.

This paper defines a new learning architecture, Layered Self-Organizing Maps (LSOMs), that uses the SOM and supervised-SOM learning algorithms. The architecture is validated with the MNIST database of hand-written digit images. LSOMs are similar to convolutional neural nets (covnets) in the way they sample data, but di…

Existence of an infinite sequence of harmonic maps between spheres of certain dimensions was proven by Bizon and Chmaj. This sequence shares many features of the Bartnik-McKinnon sequence of solutions to the Einstein-Yang-Mills equations as well as sequences of solutions that have arisen in other physical models. We ap…

Map matching of GPS trajectories from a sequence of noisy observations serves the purpose of recovering the original routes in a road network. In this work in progress, we attempt to share our experience of feature construction in a spatial database by reporting our ongoing experiment of feature extrac-tion in Conditio…

Method learns feature map between source and target domains for high-dimensional regression with missing features.

Paper proposes BTuD for unsupervised feature selection.

Study identifies and estimates causal LSNM models, proving feature maps are consistent.