Publications by Martin Jaggi | EPFL Graph Search

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.

In distributed optimization, parameter updates from the gradient computing node devices have to be aggregated in every iteration on the orchestrating server. When these updates are sent over an arbitrary commodity network, bandwidth and latency can be limi ...

Objective: Acute intracranial hypertension is an important risk factor of secondary brain damage after traumatic brain injury. Hypertensive episodes are often diagnosed reactively, leading to late detection and lost time for intervention planning. A pro-ac ...

We consider learning of fundamental properties of communities in large noisy networks, in the prototypical situation where the nodes or users are split into two classes according to a binary property, e.g., according to their opinions or preferences on a t ...

Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Keyphrases can be used for indexing, searching, aggregating and summarizing text documents, serving many automatic as well as ...

A new generation of manycore processors is on the rise that offers dozens and more cores on a chip and, in a sense, fuses host processor and accelerator. In this paper we target the efficient training of generalized linear models on these machines. We prop ...

Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy. We consider learning of linear classification and regression models, in the setting where the training data is decentralized over ma ...

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce DNNs' computatio ...

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the par ...

Background: In 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma s ...

The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing datacenter operators to adopt domain-specific accelerators to train them. These accelerators typically employ densely packed full-precision floating-point arithmetic t ...

Background After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. The efficacy and collateral damage of pandemic policies are dependent on constantly evolving viral epidemiol ...

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show that data heteroge ...

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and—in asynchronous implementations—on the gradient staleness. Especially, it has been observed that the spe ...

Two popular examples of first-order optimization methods over linear spaces are coordinate descent and matching pursuit algorithms, with their randomized variants. While the former targets the optimization by moving along coordinates, the latter considers ...

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension ...

DNN inference accelerators executing online services exhibit low average loads because of service demand variability, leading to poor resource utilization. Unfortunately, reclaiming idle inference cycles is difficult as other workloads can not execute on a ...

We study lossy 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 ...

There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shift the focus from words to documents and introduce a method for embedding doc ...

Background Lung auscultation is fundamental to the clinical diagnosis of respiratory disease. However, auscultation is a subjective practice and interpretations vary widely between users. The digitization of auscultation acquisition and interpretation is a ...

The identification of nanomaterials with the properties required for energy-efficient electronic systems is usually a tedious human task. A workflow to rapidly localize and characterize nanomaterials at the various stages of their integration into large-sc ...

Martin Jaggi

Chat with Graph Search

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Forecasting intracranial hypertension using multi-scale waveform metrics

Unsupervised Robust Nonparametric Learning Of Hidden Community Properties

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

On Linear Learning with Manycore Processors

COLA: Decentralized Linear Learning

Effective Interplay Between Sparsity and Quantization: from Theory to Practice

Ensemble Distillation for Robust Model Fusion in Federated Learning

Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study

Training DNNs with Hybrid Block Floating Point

what If...? Pandemic Policy-decision-support to Guide a Cost-benefit-optimised, Country- Specific Response

Implicit Gradient Alignment in Distributed and Federated Learning

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

On Matching Pursuit and Coordinate Descent

Efficient Greedy Coordinate Descent for Composite Problems

Equinox: Training (for Free) on a Custom Inference Accelerator

PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization

Crosslingual Document Embedding as Reduced-Rank Ridge Regression

Deep learning diagnostic and risk-stratification pattern detection for COVID-19 in digital lung auscultations: clinical protocol for a case-control and prospective cohort study

High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning