ColTraIn: Co-located DNN training and inference

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.

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

Acoustic emission (AE) monitoring is commonly used to inspect the health of a structure continuously. During fracture processes elastic waves of AE are created and emitted, and sensors can capture these waves. The acquired signals can be processed to track ...

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the ...

Machine learning and signal processing on the edge are poised to influence our everyday lives with devices that will learn and infer from data generated by smart sensors and other devices for the Internet of Things. The next leap toward ubiquitous electron ...

The Schur decomposition of a square matrix A is an important intermediate step of state-of-the-art numerical algorithms for addressing eigenvalue problems, matrix functions, and matrix equations. This work is concerned with the following task: Compute a (m ...

Developing and fine-tuning software programs for heterogeneous hardware such as CPU/GPU processing platforms comprise a highly complex endeavor that demands considerable time and effort of software engineers and requires evaluating various fundamental comp ...

Edge-computing requires high-performance energy-efficient embedded systems. Fixed-function or custom accelerators, such as FFT or FIR filter engines, are very efficient at implementing a particular functionality for a given set of constraints. However, the ...

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

Inspired by the work of Lang-Trotter on the densities of primes with fixed Frobenius traces for elliptic curves defined over Q and by the subsequent generalization of Cojocaru-Davis-Silverberg-Stange to generic abelian varieties, we study the analogous que ...

The present invention is related to an endoscopic system for phase imaging, comprising a multicore waveguide (080), an optical system comprising at least one first light source (002), for illuminating the sample to be examined, a first camera (010) that is ...

Many pathologies cause impairments in the speech production mechanism resulting in reduced speech intelligibility and communicative ability. To assist the clinical diagnosis, treatment and management of speech disorders, automatic pathological speech asses ...

Countless signal processing applications include the reconstruction of signals from few indirect linear measurements. The design of effective measurement operators is typically constrained by the underlying hardware and physics, posing a challenging and of ...

We present TimeEvolver, a program for computing time evolution in a generic quantum system. It relies on well-known Krylov subspace techniques to tackle the problem of multiplying the exponential of a large sparse matrix iH, where His the Hamiltonian, with ...

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 ...

ColTraIn: Co-located DNN training and inference

Chat with Graph Search

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Automatic and high-precision microseismic monitoring of progressive failure prior, during, and after tunnel excavation

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

Low-Power Artificial Neural Network Perceptron Based on Monolayer MoS2

Iterative refinement of Schur decompositions

Dynamic SIMD Parallel Execution on GPU from High-Level Dataflow Synthesis

VWR2A: A Very-Wide-Register Reconfigurable-Array Architecture for Low-Power Embedded Devices

Robust Binary Models by Pruning Randomly-initialized Networks

The Lang-Trotter conjecture for products of non-CM elliptic curves

Multicore fiber endoscope for phase imaging based on intensity recording using deep neural networks

Automatic pathological speech assessment

Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery

TimeEvolver: A program for time evolution with improved error bound

System Support for Robust Distributed Learning