A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper proposes reusable network components by making them compatible across tasks.
Proposes a balanced multi-component and multi-layer neural network for efficient function approximation.
Proposes ANOVA-TPNN for stable interpretation of complex functions.
New insights into how encoder-decoder networks generate attention matrices.
This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks l…
Being among the easiest ways to find meaningful structure from discrete data, Latent Dirichlet Allocation (LDA) and related component models have been applied widely. They are simple, computationally fast and scalable, interpretable, and admit nonparametric priors. In the currently popular field of network modeling, re…
Spectral denoising recovers meaningful network structure from noisy financial correlations.
We propose a new variational family for Bayesian neural networks. We decompose the variational posterior into two components, where the radial component captures the strength of each neuron in terms of its magnitude; while the directional component captures the statistical dependencies among the weight parameters. The …
Gradient descent with growing learning rate enables learning non-linear features in neural networks.
APD method decomposes neural network parameters into simple, faithful components.
Analyzes geodesic lengths in sparse networks, deriving a distribution.
FMMNN combines sine activations with multi-component, multi-layer structure for high-frequency function approximation.
Bayesian-TPNN improves ANOVA-TPNN for detecting higher-order components.
To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for m…
The ever-increasing demand from mobile Machine Learning (ML) applications calls for evermore powerful on-chip computing resources. Mobile devices are empowered with heterogeneous multi-processor Systems-on-Chips (SoCs) to process ML workloads such as Convolutional Neural Network (CNN) inference. Mobile SoCs house sever…
Study identifies components of unknown interventions in a mixture.
Study reveals hidden null components in overparametrized neural networks.
CSD learns a common component for domain generalization, outperforming existing methods.
Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer across models. We hypothesize that adversarial weakness is composed of three sources of bias: architecture, dataset, and random initialization.…
The manual design of analog circuits is a tedious task of parameter tuning that requires hours of work by human experts. In this work, we make a significant step towards a fully automatic design method that is based on deep learning. The method selects the components and their configuration, as well as their numerical …
GT-PCA improves PCA for image and time series data.
Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end. While a simple genetic algorithm recently showed end-to-e…
This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well…
Quaternion self-attention reduces computational cost and improves performance.
A new method reduces data movement in neural network training.
Deep Neural Networks for image classification have been found to be vulnerable to adversarial samples, which consist of sub-perceptual noise added to a benign image that can easily fool trained neural networks, posing a significant risk to their commercial deployment. In this work, we analyze adversarial samples throug…
Unrolled neural networks emerged recently as an effective model for learning inverse maps appearing in image restoration tasks. However, their generalization risk (i.e., test mean-squared-error) and its link to network design and train sample size remains mysterious. Leveraging the Stein's Unbiased Risk Estimator (SURE…
Eigen component analysis combines quantum mechanics with machine learning for efficient data analysis.
Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design and training of recurrent neural networks. We propose a new model, the Linear Me…
Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. W…
Despite the promising results of convolutional neural networks (CNNs), their application on devices with limited resources is still a big challenge; this is mainly due to the huge memory and computation requirements of the CNN. To counter the limitation imposed by the network size, we use pruning to reduce the network …
Despite a lack of theoretical understanding, deep neural networks have achieved unparalleled performance in a wide range of applications. On the other hand, shallow representation learning with component analysis is associated with rich intuition and theory, but smaller capacity often limits its usefulness. To bridge t…
Proposes BATer for improved adversarial example detection.
This paper proposes a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower-dimensional space using a set of orthogonal tra…
Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components. We consider a generalized PCA that aims at maximizing the sum of an arbitrary convex function of principal components. We present a gradient ascent algorithm to solve the problem. Fo…
Model combines long-term and short-term memory using conceptors.
This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing met…
Study adapts -TCVAE for fMRI to recover nonlinear brain components.
Deeper neural networks learn lower frequency functions faster, according to a new principle.
Paper addresses theoretical risks in neural MCCFR, proposing Robust Deep MCCFR for improved performance.
DeepLight accelerates CTR predictions in ad serving by 46X.
GNIs induce a regulariser that penalizes high-frequency components in neural network activations.
FA algorithm provides convergence guarantees for deep linear networks.
In this paper, we study the adversarial attack and defence problem in deep learning from the perspective of Fourier analysis. We first explicitly compute the Fourier transform of deep ReLU neural networks and show that there exist decaying but non-zero high frequency components in the Fourier spectrum of neural network…
The paper defines and analyzes feature complexity in DNNs, proposing metrics for feature disentanglement and evaluation.
A new GNN architecture called coVariance neural network (VNN) improves stability and transferability of covariance matrix analysis.
Deep equilibrium models estimate latent variables from data.
New method finds smaller networks with similar performance to large models in fewer epochs.