no code implementations • 6 Nov 2020 • Damien Scieur, Lewis Liu, Thomas Pumir, Nicolas Boumal
Quasi-Newton techniques approximate the Newton step by estimating the Hessian using the so-called secant equations.
Optimization and Control Numerical Analysis Numerical Analysis
no code implementations • NeurIPS 2019 • Chris Criscitiello, Nicolas Boumal
Specifically, for an arbitrary Riemannian manifold $\mathcal{M}$ of dimension $d$, a sufficiently smooth (possibly non-convex) objective function $f$, and under weak conditions on the retraction chosen to move on the manifold, with high probability, our version of PRGD produces a point with gradient smaller than $\epsilon$ and Hessian within $\sqrt{\epsilon}$ of being positive semidefinite in $O((\log{d})^4 / \epsilon^{2})$ gradient queries.
1 code implementation • 12 Oct 2018 • Chao Ma, Tamir Bendory, Nicolas Boumal, Fred Sigworth, Amit Singer
In this problem, the goal is to estimate a (typically small) set of target images from a (typically large) collection of observations.
no code implementations • NeurIPS 2018 • Thomas Pumir, Samy Jelassi, Nicolas Boumal
In order to overcome scalability issues, Burer and Monteiro proposed a factorized approach based on optimizing over a matrix Y of size $n$ by $k$ such that $X = YY^*$ is the SDP variable.
no code implementations • 1 Mar 2018 • Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
Semidefinite programs (SDP) are important in learning and combinatorial optimization with numerous applications.
1 code implementation • NeurIPS 2016 • Nicolas Boumal, Vladislav Voroninski, Afonso S. Bandeira
Semidefinite programs (SDPs) can be solved in polynomial time by interior point methods, but scalability can be an issue.
Optimization and Control Numerical Analysis
1 code implementation • 1 Jun 2015 • Nicolas Boumal
We propose a new algorithm to solve optimization problems of the form $\min f(X)$ for a smooth function $f$ under the constraints that $X$ is positive semidefinite and the diagonal blocks of $X$ are small identity matrices.
no code implementations • 23 Aug 2013 • Nicolas Boumal, Bamdev Mishra, P. -A. Absil, Rodolphe Sepulchre
Optimization on manifolds is a rapidly developing branch of nonlinear optimization.
no code implementations • NeurIPS 2011 • Nicolas Boumal, Pierre-Antoine Absil
We address the problem of recovering such matrices when most of the entries are unknown.