7 papers
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…
Convergence rates of regularized quasi-Newton methods without strong convexity
Shida Wang, Jalal Fadili, Peter Ochs
In this paper, we study convergence rates of the cubic regularized proximal quasi-Newton method (\csr) for solving non-smooth additive composite problems that satisfy the so-called…
Inertial Methods with Viscous and Hessian driven Damping for Non-Convex Optimization
Rodrigo Maulen-Soto, Jalal Fadili, Peter Ochs
In this paper, we aim to study non-convex minimization problems via second-order (in-time) dynamics, including a non-vanishing viscous damping and a geometric Hessian-driven dampin…
An SDE Perspective on Stochastic Inertial Gradient Dynamics with Time-Dependent Viscosity and Geometric Damping
Rodrigo Maulen-Soto, Jalal Fadili, Hedy Attouch +1
Our approach is part of the close link between continuous dissipative dynamical systems and optimization algorithms. We aim to solve convex minimization problems by means of stocha…
Learning-to-Optimize with PAC-Bayesian Guarantees: Theoretical Considerations and Practical Implementation
Michael Sucker, Jalal Fadili, Peter Ochs
We use the PAC-Bayesian theory for the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable…
Stochastic Inertial Dynamics Via Time Scaling and Averaging
Rodrigo Maulen-Soto, Jalal Fadili, Hedy Attouch +1
Our work is part of the close link between continuous-time dissipative dynamical systems and optimization algorithms, and more precisely here, in the stochastic setting. We aim to…