Coordinate descent methods are popular in machine learning and optimizat...
We study the problem of learning general (i.e., not necessarily homogene...
We study the problem of PAC learning γ-margin halfspaces with Random
Cla...
Stochastic gradient descent (SGD) is perhaps the most prevalent optimiza...
We study the problem of learning a single neuron with respect to the
L_2...
Exploiting partial first-order information in a cyclic way is arguably t...
Nonconvex optimization is central in solving many machine learning probl...
We study stochastic monotone inclusion problems, which widely appear in
...
Nonnegative (linear) least square problems are a fundamental class of
pr...
We study a class of generalized linear programs (GLP) in a large-scale
s...
We study structured nonsmooth convex finite-sum optimization that appear...
We propose the Cyclic cOordinate Dual avEraging with extRapolation
(CODE...
Projection-free conditional gradient (CG) methods are the algorithms of
...
Making the gradients small is a fundamental optimization problem that ha...
Composite minimization is a powerful framework in large-scale convex
opt...
The use of min-max optimization in adversarial training of deep neural
n...
We leverage the connections between nonexpansive maps, monotone Lipschit...
This note provides a novel, simple analysis of the method of conjugate
g...
Conditional gradient methods form a class of projection-free first-order...
We take a Hamiltonian-based perspective to generalize Nesterov's acceler...
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate sa...
Massive data centers are at the heart of the Internet. The rapid growth ...
We study the question of whether parallelization in the exploration of t...
In network routing and resource allocation, α-fair utility functions
are...
Accelerated algorithms have broad applications in large-scale optimizati...
Full-duplex (FD) wireless is an attractive communication paradigm with h...
We provide a novel accelerated first-order method that achieves the
asym...