Papers
2026
Tight lower bounds for Lipschitz geodesically convex optimization on hyperbolic space
C Criscitiello
Doubling the dimension yields a benign landscape for the squared-stress
C Criscitiello
Smooth, globally Polyak–Łojasiewicz functions are nonlinear least-squares
N Boumal, C Criscitiello, Q RebjockSlides & posters
- FoCM 2026, Invited Speaker: Slides
- Tufts Computational and Applied Math Seminar March 2026, hosted by Abiy Tasissa: Slides
- ICCOPT 2025: Slides
Negative curvature obstructs the existence of good barriers for interior-point methods
C Criscitiello, H Nieuwboer, M Walter
2025
PhD Thesis – On the Complexity of Optimization: Curved Spaces and Benign Landscapes
C CriscitielloSensor network localization has a benign landscape after low-dimensional relaxation
C Criscitiello, AD McRae, Q Rebjock, N Boumalin Mathematical Programming, 2026
Slides & posters
Cornell ORIE February 2025, hosted by Adrian Lewis: Slides
Optimization & Decision Intelligence Group at ETH Zürich November 2024, hosted by Niao He and Ya-Ping Hsieh: Slides
Quantum Information Colloquium at RUB March 2024, hosted by Michael Walter: Slides
DACO Seminar at ETHZ March 2024, hosted by Afonso Bandeira and Pedro Abdalla Teixeira: Slides
Horospherically Convex Optimization on Hadamard Manifolds Part I: Analysis and Algorithms
C Criscitiello, J KimSlides & posters
2024
Synchronization on circles and spheres with nonlinear interactions
C Criscitiello, Q Rebjock, AD McRae, N Boumal
in SIAM Journal on Applied Dynamical Systems, 2026
2023
Curvature and complexity: Better lower bounds for geodesically convex optimization
C Criscitiello, N Boumalin the proceedings of COLT, 2023
Open problem: polynomial linearly-convergent method for g-convex optimization?
C Criscitiello, D Martínez-Rubio, N Boumalin the proceedings of COLT, 2023
Accelerated Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties
D Martínez-Rubio, C Roux, C Criscitiello, S Pokutta
in the proceedings of AISTATS, 2022
2022
Negative curvature obstructs acceleration for strongly geodesically convex optimization, even with exact first-order oracles
C Criscitiello, N Boumalin the proceedings of COLT, 2022
Slides & posters
An accelerated first-order method for non-convex optimization on manifolds
C Criscitiello, N Boumal
in the Journal of Foundations of Computational Mathematics, 2023
2019
Efficiently escaping saddle points on manifolds
C Criscitiello, N Boumalin the proceedings of NeurIPS, 2019
Slides & posters
Looking for presentations? See Talks.
See Teaching & Supervision for courses and student projects.