An Evaluation of Model-Based Approaches to Sensor Data Compression

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in orde ...

The usual explanation of the efficacy of wavelet-based methods hinges on the sparsity of many real-world objects in the wavelet domain. Yet, standard wavelet-shrinkage techniques for sparse reconstruction are not competitive in practice, one reason being t ...

Codebook-based optimizations are a class of algorithmic-level transformations able to effectively reduce the computing and memory requirements of Convolutional Neural Networks (CNNs). This approach tightly limits the number of unique weights in each layer, ...

To solve unmodeled optimization problems with hard constraints, this paper proposes a novel zeroth-order approach called Safe Zeroth-order Optimization using Linear Programs (SZO-LP). The SZO-LP method solves a linear program in each iteration to find a de ...

Despite the increasing understanding of bentonite behaviour, there is still missing evidence on how different hydro-mechanical loadings, including sequences of hydration and compression, affect the fabric and the volume change behaviour of the material. It ...

The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research com ...

By the addition of entropic regularization, multimarginal optimal transport problems can be trans-formed into tensor scaling problems, which can be solved numerically using the multimarginal Sinkhorn algorithm. The main computational bottleneck of this alg ...

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

A Finite Element Model is developed to represent the mechanical behavior of WC-10 wt.% Co in compression tests. In this research, realistic three-dimensional model is obtained by slicing a sample by Focused Ion Beam and reconstituting it, resulting in two ...

The two-dimensional (2D) delamination growth in composite laminates under the Mode-II fracture condition was experimentally investigated using a novel set-up. Circular plate specimens with a centrally embedded pre-crack of two sizes were semi-clamped along ...

Model compression techniques have lead to a reduction of size and number of computations of Deep Learning models. However, techniques such as pruning mostly lack of a real co-optimization with hardware platforms. For instance, implementing unstructured pru ...

Gas bearings use pressurized gas as a lubricant to support and guide rotating machinery. These bearings have a number of advantages over traditional lubricated bearings, including higher efficiency in a variety of applications and reduced maintenance requi ...

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extra-gradient), limiting SGD updates to a sub ...

Modern media data such as 360 degrees videos and light field (LF) images are typically captured in much higher dimensions than the observers' visual displays. To efficiently browse high-dimensional media, a navigational streaming model is considered: a cli ...

As acknowledged explicitly or implicitly in most of current design codes, a high level of sustained loading has a detrimental effect on the concrete compressive strength. However, its beneficial effect in terms of deformation capacity is neglected in most ...

An Evaluation of Model-Based Approaches to Sensor Data Compression

Chat with Graph Search

Stochastic distributed learning with gradient quantization and double-variance reduction

The Sparsity of Cycle Spinning for Wavelet-Based Solutions of Linear Inverse Problems

An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

Safe Zeroth-Order Optimization Using Linear Programs

Volume change response and fabric evolution of granular MX80 bentonite along different hydro-mechanical stress paths

Latent Space Slicing for Enhanced Entropy Modeling in Learning-Based Point Cloud Geometry Compression

Low-Rank Tensor Approximations for Solving Multimarginal Optimal Transport Problems\ast

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

FEM of stress partition during compression of WC-10 wt.% Co with realistic 3D morphology

Experimental investigation of two-dimensional Mode-II delamination in composite laminates

Structured and tiled-based pruning of Deep Learning models targeting FPGA implementations

Parametric Reduced Order Model of a Gas Bearings Supported Rotor

Masked Training of Neural Networks with Partial Gradients

Landmarking for Navigational Streaming of Stored High-Dimensional Media

Influence of sustained loading on resistance and deformation capacity of reinforced concrete members in compression