Quasar convexity is a condition that allows some first-order methods to
...
We consider a setting that a model needs to adapt to a new domain under
...
Hamiltonian Monte Carlo (HMC) is a popular method in sampling. While the...
Heavy Ball (HB) nowadays is one of the most popular momentum methods in
...
We develop an algorithmic framework for solving convex optimization prob...
In the first part of this dissertation research, we develop a modular
fr...
Stochastic gradient descent (SGD) with stochastic momentum is popular in...
Over-parametrization has become a popular technique in deep learning. It...
Incorporating a so-called "momentum" dynamic in gradient descent methods...
The Heavy Ball Method, proposed by Polyak over five decades ago, is a
fi...
We consider a new variant of AMSGrad. AMSGrad RKK18 is a
popular adaptiv...
We revisit the Frank-Wolfe (FW) optimization under strongly convex const...
We consider the problem of minimizing a smooth convex function by reduci...
We consider the use of no-regret algorithms to compute equilibria for
pa...