Publication

LaMBERT: Light and Multigranular BERT

Publications associées (35)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

An unnatural exception. Profile: Piet Oudolf

Christophe van Gerrewey

A garden by Piet Oudolf confronts you in an intellectual way with the complexity of the world, as an antidote to uniformity and repetition. ...

2022

FANOK: Knockoffs in Linear Time

Quentin Rebjock

We describe a series of algorithms that efficiently implement Gaussian model-X knockoffs to control the false discovery rate on large-scale feature selection problems. Identifying the knockoff distribution requires solving a large-scale semidefinite progra ...

SIAM PUBLICATIONS2021

Computation Of A 30750-Bit Binary Field Discrete Logarithm

Arjen Lenstra, Robert Granger, Thorsten Kleinjung, Benjamin Pierre Charles Wesolowski

This paper reports on the computation of a discrete logarithm in the finite field F-230750, breaking by a large margin the previous record, which was set in January 2014 by a computation in F-29234. The present computation made essential use of the elimina ...

AMER MATHEMATICAL SOC2021

Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems

Boi Faltings, Fei Mi, Lingjing Kong, Fengyu Cai, Wanhao Zhou

As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promising re ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2021

Fast Transformers with Clustered Attention

François Fleuret, Angelos Katharopoulos, Apoorv Vyas

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making them prohibitivel ...

2020

On the Error Rate of the LoRa Modulation With Interference

Andreas Peter Burg, Alexios Konstantinos Balatsoukas Stimming, Orion Afisiadis, Matthieu Cotting

LoRa is a chirp spread-spectrum modulation developed for the Internet of Things (IoT). In this work, we examine the performance of LoRa in the presence of both additive white Gaussian noise and interference from another LoRa user. To this end, we extend an ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

A Complexity Analysis Approach for Model-based System Engineering

Dimitrios Kyritsis, Jinzhi Lu, Xiaochen Zheng, Jinwei Chen

With the increasing complexity of the highly engineered products, Model-based Systems Engineering (MBSE) is proposed to support the complexity management of the product development. As the basic of complexity management, complexity analysis is used to meas ...

IEEE2020

String Matching: Communication, Circuits, and Learning

Mika Tapani Göös

String matching is the problem of deciding whether a given n-bit string contains a given k-bit pattern. We study the complexity of this problem in three settings. - Communication complexity. For small k, we provide near-optimal upper and lower bounds on th ...

Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik GmbH, Wadern/Saarbruecken, Germany2019

On the complexity of linearizability

Jad Hamza

It was previously shown that the problem of verifying whether a finite concurrent system is linearizable can be done with an EXPSPACE complexity. However, the best known lower bound is PSPACE-hardness, and can be obtained using a reduction from control-sta ...

SPRINGER WIEN2019

Mesoscopic self-assembly: A shift to complexity

Massimo Mastrangeli

By focusing on the construction of thermodynamically stable structures, the self-assembly of mesoscopic systems has proven capable of formidable achievements in the bottom-up engineering of micro- and nanosystems. Yet, inspired by an analogous evolution in ...

2015