Concentration inequalities
Concentration inequalities deal with deviations of functions of independent random
variables from their expectation. In the last decade new tools have been introduced making …
variables from their expectation. In the last decade new tools have been introduced making …
Learning to rank for information retrieval
TY Liu - Foundations and Trends® in Information Retrieval, 2009 - nowpublishers.com
Learning to rank for Information Retrieval (IR) is a task to automatically construct a ranking
model using training data, such that the model can sort new objects according to their …
model using training data, such that the model can sort new objects according to their …
Distribution-free, risk-controlling prediction sets
While improving prediction accuracy has been the focus of machine learning in recent years,
this alone does not suffice for reliable decision-making. Deploying learning systems in …
this alone does not suffice for reliable decision-making. Deploying learning systems in …
A theoretical analysis of NDCG type ranking measures
Ranking has been extensively studied in information retrieval, machine learning and
statistics. A central problem in ranking is to design a ranking measure for evaluation of …
statistics. A central problem in ranking is to design a ranking measure for evaluation of …
Large-scale robust deep auc maximization: A new surrogate loss and empirical studies on medical image classification
Abstract Deep AUC Maximization (DAM) is a new paradigm for learning a deep neural
network by maximizing the AUC score of the model on a dataset. Most previous works of …
network by maximizing the AUC score of the model on a dataset. Most previous works of …
[BOOK][B] Introduction to high-dimensional statistics
C Giraud - 2021 - taylorfrancis.com
Praise for the first edition:"[This book] succeeds singularly at providing a structured
introduction to this active field of research.… it is arguably the most accessible overview yet …
introduction to this active field of research.… it is arguably the most accessible overview yet …
On the properties of variational approximations of Gibbs posteriors
The PAC-Bayesian approach is a powerful set of techniques to derive nonasymptotic risk
bounds for random estimators. The corresponding optimal distribution of estimators, usually …
bounds for random estimators. The corresponding optimal distribution of estimators, usually …
Local Rademacher complexities and oracle inequalities in risk minimization
V Koltchinskii - 2006 - projecteuclid.org
Let ℱ be a class of measurable functions f: S↦ 0, 1 defined on a probability space (S, A, P).
Given a sample (X 1,…, X n) of iid random variables taking values in S with common …
Given a sample (X 1,…, X n) of iid random variables taking values in S with common …
Learning with multiclass AUC: Theory and algorithms
The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as
imbalanced learning and recommender systems. The vast majority of existing AUC …
imbalanced learning and recommender systems. The vast majority of existing AUC …
Learning from corrupted binary labels via class-probability estimation
Many supervised learning problems involve learning from samples whose labels are
corrupted in some way. For example, each sample may have some constant probability of …
corrupted in some way. For example, each sample may have some constant probability of …