7 problems

The stochastic conjugate subgradient (SCS) algorithm is an online method for stochastic convex optimization, while stochastic gradient descent (SGD) methods are stochastic first-or…

Margin-condition conjecture. This can be done by assuming margin conditions that are well adapted to the geometric nature of support vector machines, such as the one proposed by St…

Signal-strength tightness conjecture. The second condition on the signal strength is tight up to an extra $\sqrt{n}$ factor; this factor is believed to be an artifact of the analys…

Let $(\bX,y) \in \mathbb{R}^{n \times d} \times \mathbb{R}^n$ be an isotropic Gaussian sample, and let SVP denote support vector proliferation, namely coincidence between the solut…

A tropical SVM uses tropical hyperplanes to separate data, with an optimal separating tropical hyperplane meaning one that optimizes the relevant separation objective in the tropic…

The data set named $\emph{colorectal}$ contains only $62$ individuals and has a significant number of outliers. The authors compare their $\emph{MM-FS}$ strategy with the…

Consider the two-class support vector machine with a training set of $n$ points, and let its solution path vary with the parameter $\mu$. The complexity of the path is measured by…