A survey on metric learning for feature vectors and structured data
The need for appropriate ways to measure the distance or similarity between data is
ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such …
ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such …
Adversarially robust generalization requires more data
L Schmidt, S Santurkar, D Tsipras… - Advances in neural …, 2018 - proceedings.neurips.cc
Abstract Machine learning models are often susceptible to adversarial perturbations of their
inputs. Even small perturbations can cause state-of-the-art classifiers with high" standard" …
inputs. Even small perturbations can cause state-of-the-art classifiers with high" standard" …
Revisiting training strategies and generalization performance in deep metric learning
Abstract Deep Metric Learning (DML) is arguably one of the most influential lines of research
for learning visual similarities with many proposed approaches every year. Although the field …
for learning visual similarities with many proposed approaches every year. Although the field …
Artificial intelligence to improve antibiotic prescribing: a systematic review
D Amin, N Garzόn-Orjuela, A Garcia Pereira… - Antibiotics, 2023 - mdpi.com
Introduction: The use of antibiotics leads to antibiotic resistance (ABR). Different methods
have been used to predict and control ABR. In recent years, artificial intelligence (AI) has …
have been used to predict and control ABR. In recent years, artificial intelligence (AI) has …
Continual learning through retrieval and imagination
Continual learning is an intellectual ability of artificial agents to learn new streaming labels
from sequential data. The main impediment to continual learning is catastrophic forgetting, a …
from sequential data. The main impediment to continual learning is catastrophic forgetting, a …
On the variable bandwidth kernel estimation of conditional U-statistics at optimal rates in sup-norm
S Bouzebda, N Taachouche - Physica A: Statistical Mechanics and its …, 2023 - Elsevier
U-statistics represent a fundamental class of statistics from modeling quantities of interest
defined by multi-subject responses. U-statistics generalize the empirical mean of a random …
defined by multi-subject responses. U-statistics generalize the empirical mean of a random …
Uniform consistency and uniform in number of neighbors consistency for nonparametric regression estimates and conditional U-statistics involving functional data
S Bouzebda, A Nezzal - Japanese Journal of Statistics and Data Science, 2022 - Springer
U-statistics represent a fundamental class of statistics arising from modeling quantities of
interest defined by multi-subject responses. U-statistics generalize the empirical mean of a …
interest defined by multi-subject responses. U-statistics generalize the empirical mean of a …
Weak convergence of the conditional U-statistics for locally stationary functional time series
I Soukarieh, S Bouzebda - Statistical Inference for Stochastic Processes, 2024 - Springer
In recent years, the direction has turned to non-stationary time series. Here the situation is
more complicated: it is often unclear how to set down a meaningful asymptotic for non …
more complicated: it is often unclear how to set down a meaningful asymptotic for non …
Generalization guarantee of SGD for pairwise learning
Recently, there is a growing interest in studying pairwise learning since it includes many
important machine learning tasks as specific examples, eg, metric learning, AUC …
important machine learning tasks as specific examples, eg, metric learning, AUC …
Sharper generalization bounds for pairwise learning
Pairwise learning refers to learning tasks with loss functions depending on a pair of training
examples, which includes ranking and metric learning as specific examples. Recently, there …
examples, which includes ranking and metric learning as specific examples. Recently, there …