22 citations · 38 across the 9 of their papers we have counts for
9 papers
On the Convergence of Proximal Algorithms for Weakly-convex Min-max Optimization
Guido Tapia-Riera, Camille Castera, Nicolas Papadakis
We study alternating first-order algorithms with no inner loops for solving nonconvex-strongly concave min-max problems. We show the convergence of the alternating gradient descent…
Stochastic Adaptive Gradient Descent Without Descent
Jean-François Aujol, Jérémie Bigot, Camille Castera
We introduce a new adaptive step-size strategy for convex optimization with stochastic gradient that exploits the local geometry of the objective function only by means of a first-…
From Learning to Optimize to Learning Optimization Algorithms
Camille Castera, Peter Ochs
Towards designing learned optimization algorithms that are usable beyond their training setting, we identify key principles that classical algorithms obey, but have up to now, not…
Accelerated Gradient Dynamics on Riemannian Manifolds: Faster Rate and Trajectory Convergence
Tejas Natu, Camille Castera, Jalal Fadili +1
In order to minimize a differentiable geodesically convex function, we study a second-order dynamical system on Riemannian manifolds with an asymptotically vanishing damping term o…
Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization
Severin Maier, Camille Castera, Peter Ochs
We introduce an autonomous system with closed-loop damping for first-order convex optimization. While, to this day, optimal rates of convergence are almost exclusively achieved by…
Continuous Newton-like Methods featuring Inertia and Variable Mass
Camille Castera, Hedy Attouch, Jalal Fadili +1
We introduce a new dynamical system, at the interface between second-order dynamics with inertia and Newton's method. This system extends the class of inertial Newton-like dynamics…
Inertial Newton Algorithms Avoiding Strict Saddle Points
Camille Castera
We study the asymptotic behavior of second-order algorithms mixing Newton's method and inertial gradient descent in non-convex landscapes. We show that, despite the Newtonian behav…
Second-order step-size tuning of SGD for non-convex optimization
Camille Castera, Jérôme Bolte, Cédric Févotte +1
In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case. For doing so, one estimates curvature, based…
An Inertial Newton Algorithm for Deep Learning
Camille Castera, Jérôme Bolte, Cédric Févotte +1
We introduce a new second-order inertial optimization method for machine learning called INNA. It exploits the geometry of the loss function while only requiring stochastic approxi…