arXiv research

A new clustering algorithm considers data smoothness for better performance.

This paper represents a preliminary (pre-reviewing) version of a sublinear variational algorithm for isotropic Gaussian mixture models (GMMs). Further developments of the algorithm for GMMs with diagonal covariance matrices (instead of isotropic clusters) and their corresponding benchmarking results have been published…

Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text…

IMPACC improves consensus clustering for bioinformatics data.

Tiny Eats GRU detects eating episodes on a microcontroller.

Finding Tiny Faces (by Hu and Ramanan) proposes a novel approach to find small objects in an image. Our contribution consists in deeply understanding the choices of the paper together with applying and extending a similar method to a real world subject which is the counting of people in a public demonstration.

Tiny complexes share 3-5 triangles in common coverings.

Tab-TRM uses recursive model for insurance pricing on tabular data.

Tiny benchmarks reduce LLM evaluation costs by using fewer examples.

New algorithm PRACTISE accelerates networks with tiny sets, reducing latency by 22%.

ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YO…

Study Lie algebras with complex structures, focusing on degenerations and deformations.

Paper proposes a GPU-based system for training massive deep learning models in ads systems.

Flat space for manifolds with tiny curvature.

Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.

Puzzle Mix optimizes mixup by leveraging saliency and local statistics.

This work analyzes how frequency components affect CNN predictions and robustness.

Softmax is found ineffective for NL block, leading to improved performance.

AL$\ell_0$CORE tensor decomposition reduces computational cost for sparse count data.

POET enables large neural network training on tiny devices with reduced energy.

Improved bound for optimal Moebius band aspect ratio.

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform …

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-g…

Improved robustness of machine learning models with controlled Lipschitz constants.

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have incre…

We show that in a variety of large-scale deep learning scenarios the gradient dynamically converges to a very small subspace after a short period of training. The subspace is spanned by a few top eigenvectors of the Hessian (equal to the number of classes in the dataset), and is mostly preserved over long periods of tr…

A new mutual information optimization method using self-supervised binary contrastive learning.

Review of efficient neural networks for TinyML on resource-constrained devices.

Sharp results link DLN gradient flow to basis pursuit optimization and GHA phase transitions.

Paper trains a Transformer to add numbers of any length.

FLaPS improves scalability and privacy in federated learning.

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the tra…

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including deep learning models, are highly vulnerable to adversarial attacks.…

New framework explains adversarial examples in neural nets.

In this short article we investigate the topology of the moduli space of two-convex embedded tori $S^{n-1}\times S^1\subset \mathbb{R}^{n+1}$. We prove that for $n \geq 3$ this moduli space is path-connected, and that for $n = 2$ the connected components of the moduli space are in bijective correspondence with the knot…

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed …

Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We s…

A new approach of solving the ill-conditioned inverse problem for analytical continuation is proposed. The root of the problem lies in the fact that even tiny noise of imaginary-time input data has a serious impact on the inferred real-frequency spectra. By means of a modern regularization technique, we eliminate redun…

Proposes a method to improve neural architectures reproducibly.

GraphXCOVID uses deep semi-supervised learning to identify COVID-19 from chest X-rays with minimal labels.

Efficiently estimates Gaussian distributions privately and robustly.

This work analyzes the Gompertz-Pareto distribution (GPD) of personal income, formed by the combination of the Gompertz curve, representing the overwhelming majority of the economically less favorable part of the population of a country, and the Pareto power law, which describes its tiny richest part. Equations for the…

The paper examines stable CMC hypersurfaces with boundaries on parallel hyperplanes.

A new learning scheme improves model efficiency and performance.

Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows that most of the activation gradients in back-propagation are very close to zero…

Understanding how neural networks learn remains one of the central challenges in machine learning research. From random at the start of training, the weights of a neural network evolve in such a way as to be able to perform a variety of tasks, like classifying images. Here we study the emergence of structure in the wei…

Image classifiers are sensitive to small changes, affecting most images in a class.