Do you know the difference between an optimist and a pessimist? The former believes we
live in the best possible world, and the latter is afraid that the former might be right.… In that …

We study the problem of algorithmically optimizing the Hamiltonian HN H_N of a spherical or
Ising mixed pp‐spin glass. The maximum asymptotic value OPT OPT of HN/N H_N/N is …

We present a Newton-type method that converges fast from any initialization and for arbitrary
convex objectives with Lipschitz Hessians. We achieve this by merging the ideas of cubic …

In this paper, we study the fundamental open question of finding the optimal high-order
algorithm for solving smooth convex minimization problems. Arjevani et al.(2019) …

We analyze the performance of a variant of the Newton method with quadratic regularization
for solving composite convex minimization problems. At each step of our method, we choose …

Gradient-free/zeroth-order methods for black-box convex optimization have been
extensively studied in the last decade with the main focus on oracle calls complexity. In this …

This paper is a survey of methods for solving smooth,(strongly) monotone stochastic
variational inequalities. To begin with, we present the deterministic foundation from which …

In this paper, we present the first stepsize schedule for Newton method resulting in fast
global and local convergence guarantees. In particular, we a) prove an $\mathcal O\left …

Consider an oracle which takes a point x and returns the minimizer of a convex function f in
an l2 ball of radius r around x. It is straightforward to show that roughly r^{-1}\log (1/epsilon) …

In this paper, we complement the framework of bilevel unconstrained minimization (BLUM)
Y. Nesterov, Math. Program., to appear by a new p th-order proximal-point method …