Dalton: Learned Partitioning for Distributed Data Streams

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.

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

Objective To develop and validate a wrist‐worn accelerometer‐based, deep‐learning tunable algorithm for the automated detection of generalized or bilateral convulsive seizures (CSs) to be integrated with off‐the‐shelf smartwatches. Methods We conducted a ...

Humans can rapidly estimate the statistical properties of groups of stimuli, including their average and variability. But recent studies of so-called Feature Distribution Learning (FDL) have shown that observers can quickly learn even more complex aspects ...

Recently, several theories including the replica method made predictions for the generalization error of Kernel Ridge Regression. In some regimes, they predict that the method has a 'spectral bias': decomposing the true function f* on the eigenbasis of the ...

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

Writing and optimizing application software for heterogeneous platforms including GPU units is a very difficult task that requires designer efforts and resources to consider several key elements to obtain good performance. Dataflow programming has shown to ...

Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor loc ...

Machine learning (ML) applications are ubiquitous. They run in different environments such as datacenters, the cloud, and even on edge devices. Despite where they run, distributing ML training seems the only way to attain scalable, high-quality learning. B ...

This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal disc ...

Lightning causes significant damage and casualties globally by directly striking humans and livestock, by igniting forest fires, and by inducing electrical surges in electronic infrastructure, airplanes, rockets, etc. Monitoring the evolution of thundersto ...

The ability to predict the spatial distribution of tree root system variables (e.g., the Root system Area (RA), the maximum root diameter, the number of roots in diameter classes, the density of fine roots, etc.) under different environmental conditions is ...

Under the trends of multifunctionality, tunability, and compactness in modern wave -based signal processors, in this paper, we propose a polarization-multiplexed graphene-based metasurface to realize distinct mathematical operators on the parallel time-dom ...

Chemical gas dispersion can represent a severe threat to human and animal lives, as well as to the environment. Constructing a map of the distribution of gas in a fast and reliable manner is critical to ensure accurate monitoring of at-risk facilities and ...

Timely insights lead to business growth and scientific breakthroughs but require analytical engines that cope with the ever-increasing data processing needs. Analytical engines relied on rapid CPU improvements, yet the end of Dennard scaling stopped the fr ...

Despite the high number of investments for data-based models in the expansion of Industry 4.0, too little effort has been made to ensure the maintenance of those models. In a data-streaming environment, data-based models are subject to concept drifts. A co ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

High-level synthesis (HLS) tools typically generate statically scheduled datapaths. Static scheduling implies that the resulting circuits have a hard time exploiting parallelism in code with potential memory dependences, with control dependences, or where ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

When applied to new datasets, acquired at different time moments, with different sensors or under different acquisition conditions, deep learning models might fail spectacularly. This is because they have learned from the data distribution observed during ...

Atomistic simulations performed with a family of model potential with tunable hardness have proven to be a great tool for advancing the understanding of wear processes at the asperity level. They have been instrumental in finding a critical length scale, w ...

Dalton: Learned Partitioning for Distributed Data Streams

Chat with Graph Search

Person Re-Identification and its Application to Multi-Object Tracking

Deep learning–based detection of generalized convulsive seizures using a wrist‐worn accelerometer

Feature distribution learning by passive exposure

Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

SIMD Parallel Execution on GPU from High-Level Dataflow Synthesis

Memory of Motion for Initializing Optimization in Robotics

System Support for Robust Distributed Learning

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

On the Use of Benford’s Law to Assess the Quality of the Data Provided by Lightning Locating Systems

Tree root distribution modelling in different environmental conditions

Parallel temporal signal processing enabled by polarization-multiplexed programmable THz metasurfaces

Clustering and Informative Path Planning for 3D Gas Distribution Mapping: Algorithms and Performance Evaluation

Efficient Analytical Query Processing on CPU-GPU Hardware Platforms

Data-based model maintenance in the era of industry 4.0: A methodology

Understanding generalization and robustness in modern deep learning

From C/C plus plus Code to High-Performance Dataflow Circuits

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Deep Domain Adaptation in Earth Observation

A story of two transitions: From adhesive to abrasive wear and from ductile to brittle regime