🥭 MANGO: Maximization of neural Activation via Non-Gradient Optimization

Hierarchical Tucker for Black Box approximation and optimization

Numerical experiments for Optima-TT method from teneva python package. This method finds items which relate to min and max elements of the tensor in the tensor train (TT) format.

Black-box adversarial attacks on deep neural networks with tensor train (TT) decomposition and PROTES optimizer.

Gradient-free optimization method for the multidimensional arrays and discretized multivariate functions based on the tensor train (TT) format.

Gradient-free optimization method for multivariable functions based on the low rank tensor train (TT) format and maximal-volume principle.

Solver in the low-rank tensor train format with cross approximation approach for the multidimensional Fokker-Planck equation

A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays