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.
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
CTT compresses samples to test distributions near-linearly, outperforming existing methods.
PowerGossip compresses model differences for decentralized deep learning with low-rank linear compressors.
A recent paper (\cite{BJM}) by Biringer, Johnson, and Minsky prove that any pseudo-Anosov whose stable lamination is the limit of disks in a compression body has a power which extends over some non-trivial minimal compression body. This paper presents an alternative proof of their theorem, using techniques of Long and …
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
Lossless compression of deep neural networks using NTK and RMT.
This work proves that large models can be compressed significantly without losing performance.
Sketching reduces data size for accurate spectral estimation.
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…
As a lossy compression framework, compressed sensing has drawn much attention in wireless telemonitoring of biosignals due to its ability to reduce energy consumption and make possible the design of low-power devices. However, the non-sparseness of biosignals presents a major challenge to compressed sensing. This study…
The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitutes a powerful tool to compress convolutional neural networks (CNNs) by decomposing the 4-way kernel tensor into multi-stage smaller ones. Bu…
We study gradient compression methods to alleviate the communication bottleneck in data-parallel distributed optimization. Despite the significant attention received, current compression schemes either do not scale well or fail to achieve the target test accuracy. We propose a new low-rank gradient compressor based on …
Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the weight matrices of fully connected layers. In recent years, tensor regression networks have been investigated from the perspective of their comp…
This article proposes a novel solution for stretchy polynomial regression learning. The solution comes in primal and dual closed-forms similar to that of ridge regression. Essentially, the proposed solution stretches the covariance computation via a power term thereby compresses or amplifies the estimation. Our experim…
We show that a pseudo-Anosov map on a boundary component of an irreducible 3-manifold has a power that partially extends to the interior if and only if its (un)stable lamination is a projective limit of meridians. The proof is through 3-dimensional hyperbolic geometry, and involves an investigation of algebraic limits …
An extension of the regularized least-squares in which the estimation parameters are stretchable is introduced and studied in this paper. The solution of this ridge regression with stretchable parameters is given in primal and dual spaces and in closed-form. Essentially, the proposed solution stretches the covariance c…
Paper improves MIRACLE for faster, more robust neural network compression.
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be comp…
This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.
Algorithm estimates principal eigenvector with adaptive sensing, improving over non-adaptive methods.
Over the years, ensemble methods have become a staple of machine learning. Similarly, generalized linear models (GLMs) have become very popular for a wide variety of statistical inference tasks. The former have been shown to enhance out- of-sample predictive power and the latter possess easy interpretability. Recently,…
Improves probability distribution compression with KT algorithm.
Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the compressed data domain. The idea is to reduce the data dimension by Variational…
The online problem of computing the top eigenvector is fundamental to machine learning. In both adversarial and stochastic settings, previous results (such as matrix multiplicative weight update, follow the regularized leader, follow the compressed leader, block power method) either achieve optimal regret but run slow,…
Deep neural networks (DNNs) have been expanded into medical fields and triggered the revolution of some medical applications by extracting complex features and achieving high accuracy and performance, etc. On the contrast, the large-scale network brings high requirements of both memory storage and computation resource,…
Modern deep learning models are often trained in parallel over a collection of distributed machines to reduce training time. In such settings, communication of model updates among machines becomes a significant performance bottleneck and various lossy update compression techniques have been proposed to alleviate this p…
Goal: This paper deals with the problems that some EEG signals have no good sparse representation and single channel processing is not computationally efficient in compressed sensing of multi-channel EEG signals. Methods: An optimization model with L0 norm and Schatten-0 norm is proposed to enforce cosparsity and low r…
Efficiently compress overparameterized deep models by focusing on low-dimensional learning dynamics.
A new deep learning framework for efficient IoT data compression and inference.
Paper uses SGLD to recover signals from generative models, proving convergence under mild conditions.
Efficiently compress pretrained models using RSI for improved predictive accuracy.
In this paper, we derive Hybrid, Bayesian and Marginalized Cramér-Rao lower bounds (HCRB, BCRB and MCRB) for the single and multiple measurement vector Sparse Bayesian Learning (SBL) problem of estimating compressible vectors and their prior distribution parameters. We assume the unknown vector to be drawn from a compr…
Paper compresses deep neural networks by eliminating redundant neurons.
New method preserves privacy while improving machine learning accuracy.
In this paper, we consider the joint design of data compression and 802.15.4-based medium access control (MAC) protocol for smartgrids with renewable energy. We study the setting where a number of nodes, each of which comprises electricity load and/or renewable sources, report periodically their injected powers to a da…
Investigates principles of generalization in list learning, refutes sample compression conjecture.
Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art GANs often use tens of millions of parameters, making them expensive to deploy for applications in low SWAP (size, weight, and power) hardwar…
The implementation of Deep Convolutional Neural Networks (ConvNets) on tiny end-nodes with limited non-volatile memory space calls for smart compression strategies capable of shrinking the footprint yet preserving predictive accuracy. There exist a number of strategies for this purpose, from those that play with the to…
Data pruning algorithms struggle in high compression regimes, as shown by theoretical and empirical studies.
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…
Adjoined Networks trains both base and compressed networks together for efficient model compression.
We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds to hierarchical nonlinear tensor decomposition. We propose to solve the learning…
CTE improves explanation estimation with less data and faster computation.
Integrating wind power into the grid is challenging because of its random nature. Integration is facilitated with accurate short-term forecasts of wind power. The paper presents a spatio-temporal wind speed forecasting algorithm that incorporates the time series data of a target station and data of surrounding stations…
We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with entries so that the training loss of the quantized net is minimal. The codebook can be optimally learned jointly with the net, or fixed, as for bina…
Spectral clustering is one of the most widely used techniques for extracting the underlying global structure of a data set. Compressed sensing and matrix completion have emerged as prevailing methods for efficiently recovering sparse and partially observed signals respectively. We combine the distance preserving measur…
Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing inp…
Meta learning optimizes neural network quantization for efficient inference.