5 papers · 1 filter
Prox-NAG-GS: A Semi-Implicit Proximal Method for Composite Optimization
Sikeh Gisele Wiykiynyuy, Kelvin Asu Ekuri, Valentin Leplat
Composite optimization problems, where a smooth loss is combined with a nonsmooth regularizer, are common in machine learning and inverse problems. In this work, we study a proxima…
IRON: Implicit Resolvent Optimization under Noise
Valentin Leplat, Roland Hildebrand
We study stochastic optimization from a joint continuous-discrete point of view. Starting from a second-order stochastic differential equation interpreted as a noisy accelerated gr…
Joint Majorization-Minimization for Nonnegative CP and Tucker Decompositions under -Divergences: Unfolding-Free Updates
Valentin Leplat
We study majorization-minimization methods for nonnegative tensor decompositions under the -divergence family, focusing on nonnegative CP and Tucker models. Our aim is to avoid…
Constrained Optimization via Constraint-Induced Geometry: Implicit Feasible Dynamics and Optimality from Stationarity
Valentin Leplat
We introduce Gravidy, a geometry-aware framework for constrained optimization in which constraints are encoded directly into the dynamics, so the motion remains feasible by constru…
Norm-Constrained Flows and Sign-Based Optimization: Theory and Algorithms
Valentin Leplat, Sergio Mayorga, Roland Hildebrand +1
Sign Gradient Descent (SignGD) uses only the coordinate-wise sign of the gradient. We study this method through norm-constrained continuous-time dynamics: at each point, the veloci…