5 problems

Minimum attention is defined by the control-change functional … Here $u$ is a control varying over state space $\Omega$ and time interval $[0,T]$, and the functional penalizes chan…

Let \texttt{MADA}\xspace\ be a meta-adaptive optimizer that learns interpolation coefficients, and let \texttt{MADA}\xspace\-FS denote the version using the fixed final optimiz…

Task-diversity conjecture. We conjecture that this alternation is caused by the greater variance in meta-training arising from the higher diversity in tasks.

Let BSGD denote the biased stochastic first-order algorithm proposed for conditional stochastic optimization. For strongly convex and weakly convex objectives, the BSGD optimality…

A surrogate-based optimization framework uses a surrogate model for the true objective function and a model of a substitution strategy, called a relevator, to decide whether a cand…