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.
Distributed sensors compress and send features to a fusion center for linear regression.
Paper tackles noisy labels by compressing feature representations.
The emergence of various intelligent mobile applications demands the deployment of powerful deep learning models at resource-constrained mobile devices. The device-edge co-inference framework provides a promising solution by splitting a neural network at a mobile device and an edge computing server. In order to balance…
This paper compresses large datasets for efficient machine learning.
Bayesian neural networks are compressed using feature and weight pruning based on posterior inclusion probabilities.
Dirichlet pruning compresses neural networks by removing unimportant units.
New approach for learning large Bayesian networks using feature clustering and compression.
One-bit quantization improves inference speed for Random Features models.
Neural networks compress uninformative input directions, improving test error.
Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method call…
Chromatic Learning reduces feature dimensions for sparse datasets.
FEDS distills LIC model knowledge into a lightweight student for efficient compression.
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need for compression techniques that can achieve significant compression wit…
Compressive Sensing (CS) theory asserts that sparse signal reconstruction is possible from a small number of linear measurements. Although CS enables low-cost linear sampling, it requires non-linear and costly reconstruction. Recent literature works show that compressive image classification is possible in CS domain wi…
New guarantees for asymmetric sketching in compressive learning.
We describe a general framework -- compressive statistical learning -- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A…
Nonparametric regression for massive numbers of samples (n) and features (p) is an increasingly important problem. In big n settings, a common strategy is to partition the feature space, and then separately apply simple models to each partition set. We propose an alternative approach, which avoids such partitioning and…
We simplify complex regression coefficients using linearization and feature comparison.
The paper defines and analyzes feature complexity in DNNs, proposing metrics for feature disentanglement and evaluation.
AdaBoost improves binary classification in robust one-bit compressed sensing with adversarial errors.
COIN++ compresses multiple data types efficiently.
Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore specialized areas for exploration and design of large spaces in terms of size, spe…
New method compresses deep learning layers using tensor decomposition.
Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational Autoencoders (VQ-VAEs), we motivate the us…
We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques. Gesture features are extracted directly from the compressed measurements, which are the block averages and the coded linear combinations of the image sensor's pixel values. We also improve both the co…
A new method for high-dimensional data classification reduces misclassification errors.
We present a new similarity measure based on information theoretic measures which is superior than Normalized Compression Distance for clustering problems and inherits the useful properties of conditional Kolmogorov complexity. We show that Normalized Compression Dictionary Size and Normalized Compression Dictionary En…
Compression-based similarity measures are effectively employed in applications on diverse data types with a basically parameter-free approach. Nevertheless, there are problems in applying these techniques to medium-to-large datasets which have been seldom addressed. This paper proposes a similarity measure based on com…
This paper presents the philosophy, design and feature-set of Neural Network Distiller, an open-source Python package for DNN compression research. Distiller is a library of DNN compression algorithms implementations, with tools, tutorials and sample applications for various learning tasks. Its target users are both en…
CTE improves explanation estimation with less data and faster computation.
Gradual pruning reduces inference cost by pruning least important channels during training.
Paper proposes Nyström sketches for better adaptive compressive learning.
Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a generative model. We search and constrain on latent variable space to make the m…
GrateTile optimizes CNN feature map storage for efficient data access.
We solve the compressive sensing problem via convolutional factor analysis, where the convolutional dictionaries are learned {\em in situ} from the compressed measurements. An alternating direction method of multipliers (ADMM) paradigm for compressive sensing inversion based on convolutional factor analysis is develope…
This paper proposes a new method to compress CNNs for medical image analysis, improving efficiency and accuracy.
Improved survival analysis using square root Cox's models and neural networks.
Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redunda…
Three new efficient algorithms project vectors onto weighted l1 ball.
In the era of big data, learning from categorical features with very large vocabularies (e.g., 28 million for the Criteo click prediction dataset) has become a practical challenge for machine learning researchers and practitioners. We design a highly-scalable vocabulary compression algorithm that seeks to maximize the …
New method compresses large sample data for faster discriminant analysis.
We learn sparse precision matrices from compressed data sketches.
Over-the-counter markets are at the center of the postcrisis global reform of the financial system. We show how the size and structure of such markets can undergo rapid and extensive changes when participants engage in portfolio compression, a post-trade netting technology. Tightly-knit and concentrated trading structu…
This thesis responds to the challenges of using a large number, such as thousands, of features in regression and classification problems. There are two situations where such high dimensional features arise. One is when high dimensional measurements are available, for example, gene expression data produced by microarray…
New framework compresses and recovers scientific data efficiently.
An increasing amount of civil engineering applications are utilising data acquired from infrastructure instrumented with sensing devices. This data has an important role in monitoring the response of these structures to excitation, and evaluating structural health. In this paper we seek to monitor pedestrian-events (su…
Improved BIRCH clustering method to avoid numeric issues.
G-CREWE efficiently aligns large networks using node embeddings and compression.