We study the learnability of linear threshold functions (LTFs) in the learning from label
proportions (LLP) framework. In this, the feature-vector classifier is learnt from bags of …

We study the problem of properly learning linear threshold functions (LTFs) in the learning
from label proportions (LLP) framework. In this, the learning is on a collection of bags of …

Learning from label proportions (LLP) is a generalization of supervised learning in which the
training data is available as sets or bags of feature-vectors (instances) along with the …

A simple way to generate a Boolean function is to take the sign of a real polynomial in n
variables. Such Boolean functions are called polynomial threshold functions. How many low …

We study the problem of {\em properly} learning large margin halfspaces in the agnostic
PAC model. In more detail, we study the complexity of properly learning $ d $-dimensional …

A fundamental notion of distance between train and test distributions from the field of domain
adaptation is discrepancy distance. While in general hard to compute, here we provide the …

The notion of margin loss has been central to the development and analysis of algorithms for
binary classification. To date, however, there remains no consensus as to the analogue of …

For $ S\subseteq\{0, 1\}^ n $ a Boolean function $ f\colon S\to\{-1, 1\} $ is a polynomial
threshold function (PTF) of degree $ d $ and weight $ W $ if there is a polynomial $ p $ with …

The problem of learning t-term DNF formulas (for t= O (1)) has been studied extensively in
the PAC model since its introduction by Valiant (STOC 1984). A t-term DNF can be efficiently …

The degree-d Chow parameters of a Boolean function are its degree at most d Fourier
coefficients. It is well-known that degree-d Chow parameters uniquely characterize degree-d …