The BFGS quasi-Newton method is benchmarked on the noiseless BBOB-2009 testbed. A multistart strategy is applied with a maximum number of function evaluations of 105 times the sea...
We prove an upper bound on the convergence rate of Markov Chain Monte Carlo (MCMC) algorithms for the important special case when the state space can be aggregated into a smaller ...
In this paper, we study an online learning algorithm in Reproducing Kernel Hilbert Spaces (RKHS) and general Hilbert spaces. We present a general form of the stochastic gradient m...
By its dual representation, a developable surface can be viewed as a curve of dual projective 3-space. After introducing an appropriate metric in the dual space and restricting ou...
The BFGS quasi-Newton method is benchmarked on the noisy BBOB-2009 testbed. A multistart strategy is applied with a maximum number of function evaluations of about 104 times the s...