We study universal rates for multiclass classification, establishing the...
We study a generalization of boosting to the multiclass setting. We intr...
We study the problem of sequential prediction in the stochastic setting ...
There is an increasing concern that generative AI models may produce out...
When two different parties use the same learning rule on their own data,...
We provide a unified framework for characterizing pure and approximate
d...
Replicability is essential in science as it allows us to validate and ve...
We study multiclass online prediction where the learner can predict usin...
In this work we introduce an interactive variant of joint differential
p...
A classical result in online learning characterizes the optimal mistake ...
We study several variants of a combinatorial game which is based on Cant...
We first prove that Littlestone classes, those which model theorists cal...
Consider the task of learning a hypothesis class ℋ in the
presence of an...
Learning curves plot the expected error of a learning algorithm as a fun...
We present a PAC-Bayes-style generalization bound which enables the
repl...
We study the mutual information between (certain summaries of) the outpu...
Given a learning task where the data is distributed among several partie...
Supervised learning typically relies on manual annotation of the true la...
A natural procedure for assigning students to classes in the beginning o...
A seminal result in learning theory characterizes the PAC learnability o...
The amount of training-data is one of the key factors which determines t...
We study the connections between three seemingly different combinatorial...
In this work, we investigate the expressiveness of the "conditional mutu...
Hypothesis Selection is a fundamental distribution learning problem wher...
We use algorithmic methods from online learning to revisit a key idea fr...
We extend the theory of PAC learning in a way which allows to model a ri...
Which classes can be learned properly in the online model? – that is, by...
Laws of large numbers guarantee that given a large enough sample from so...
How quickly can a given class of concepts be learned from examples? It i...
We provide a negative resolution to a conjecture of Steinke and Zakynthi...
We initiate the study of a new model of supervised learning under privac...
PAC-Bayes is a useful framework for deriving generalization bounds which...
The classical PAC sample complexity bounds are stated for any Empirical ...
We study the problem of differentially private query release assisted by...
Let H be a class of boolean functions and consider acomposed class H' th...
Boosting is a widely used machine learning approach based on the idea of...
We prove that every concept class with finite Littlestone dimension can ...
We consider boosting algorithms under the restriction that the weak lear...
We consider learning problems where the training set consists of two typ...
We study the Convex Set Disjointness (CSD) problem, where two players ha...
We introduce a variant of the k-nearest neighbor classifier in which k i...
We study the relationship between the notions of differentially private
...
We present a private learner for halfspaces over an arbitrary finite dom...
We study a classic algorithmic problem through the lens of statistical
l...
Consider the following problem: given two arbitrary densities q_1,q_2 an...
We introduce two mathematical frameworks for foolability in the context ...
We examine connections between combinatorial notions that arise in machi...
`Twenty questions' is a guessing game played by two players: Bob thinks ...
We show that any family of subsets A⊆ 2^[n] satisfies
A≤ O(n^d/2), wher...
We study and provide exposition to several phenomena that are related to...