Home /
Research
Showing 649 - 654 / 897
Improving Neural Network Training in Low Dimensional Random Bases
FrithjofGressmann, ZachEaton-Rosen, CarloLuschi....
Published date-11/09/2020
Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a …
Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodel
FrancescoSannaPassino, NicholasA.Heard, PatrickRubin-Delanchy....
Published date-11/09/2020
Clustering, CommunityDetection, ModelSelection
Spectral clustering is a popular method for community detection in networks under the assumption of the standard stochastic blockmodel. Taking a matrix representation of the graph such as the adjacency …
Adversarial Semantic Collisions
CongzhengSong, AlexanderM.Rush, VitalyShmatikov....
Published date-11/09/2020
ParaphraseIdentification
We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for …
Sparsely constrained neural networks for model discovery of PDEs
Gert-JanBoth, RemyKusters....
Published date-11/09/2020
Sparse regression on a library of candidate features has developed as the prime method to discover the PDE underlying a spatio-temporal dataset. As these features consist of higher order derivatives, …
CxGBERT: BERT meets Construction Grammar
HarishTayyarMadabushi, LaurenceRomain, DagmarDivjak....
Published date-11/09/2020
While lexico-semantic elements no doubt capture a large amount of linguistic information, it has been argued that they do not capture all information contained in text. This assumption is central …
SplitEasy: A Practical Approach for Training ML models on Mobile Devices in a split second
KamaleshPalanisamy, VivekKhimani, MoinHussainMoti....
Published date-11/09/2020
Modern mobile devices, although resourceful, cannot train state-of-the-art machine learning models without the assistance of servers, which require access to privacy-sensitive user data. Split learning has recently emerged as a …