Chris Criscitiello

According to our database, Chris Criscitiello authored at least 8 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

An Accelerated First-Order Method for Non-convex Optimization on Manifolds.

Christopher Criscitiello, Nicolas Boumal

Found. Comput. Math., August, 2023

Open Problem: Polynomial linearly-convergent method for geodesically convex optimization?

Christopher Criscitiello, David Martínez-Rubio, Nicolas Boumal

CoRR, 2023

Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties.

David Martínez-Rubio, Christophe Roux, Christopher Criscitiello, Sebastian Pokutta

CoRR, 2023

Open Problem: Polynomial linearly-convergent method for g-convex optimization?

Christopher Criscitiello, David Martínez-Rubio, Nicolas Boumal

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Curvature and complexity: Better lower bounds for geodesically convex optimization.

Christopher Criscitiello, Nicolas Boumal

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Negative curvature obstructs acceleration for strongly geodesically convex optimization, even with exact first-order oracles.

Christopher Criscitiello, Nicolas Boumal

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Negative curvature obstructs acceleration for geodesically convex optimization, even with exact first-order oracles.

Christopher Criscitiello, Nicolas Boumal

CoRR, 2021

2019

Efficiently escaping saddle points on manifolds.

Chris Criscitiello, Nicolas Boumal

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019