We prove a new generalization of the higher-order Cheeger inequality for...
We study the problem of finding elements in the intersection of an arbit...
The most widely used technique for solving large-scale semidefinite prog...
We consider multi-party protocols for classification that are motivated ...
We provide a convergence analysis of gradient descent for the problem of...
Existing weak supervision approaches use all the data covered by weak si...
We present polynomial time and sample efficient algorithms for learning ...
Several works have shown that perturbation stable instances of the MAP
i...
We prove that the alpha-expansion algorithm for MAP inference always ret...
We study the problem of learning a mixture of two subspaces over
𝔽_2^n. ...
This chapter studies the problem of decomposing a tensor into a sum of
c...
Robustness is a key requirement for widespread deployment of machine lea...
We consider the problem of scheduling n precedence-constrained jobs on m...
Adversarial or test time robustness measures the susceptibility of a mac...
We study the design of computationally efficient algorithms with provabl...
Smoothed analysis is a powerful paradigm in overcoming worst-case
intrac...
To understand the empirical success of approximate MAP inference, recent...
Dictionary learning is a popular approach for inferring a hidden basis o...
The Euclidean k-means problem is arguably the most widely-studied cluste...
Gaussian mixture models (GMM) are the most widely used statistical model...
Approximate algorithms for structured prediction problems---such as the
...
We consider the problem of efficiently learning mixtures of a large numb...
Low rank tensor decompositions are a powerful tool for learning generati...