2 citations · 2 across the 6 of their papers we have counts for
9 papers
Importance Sampling Optimization with Laplace Principle
Radu-Alexandru Dragomir, François Portier, Victor Priser
Grid search and random search are widely used techniques for hyperparameter tuning in machine learning, especially when gradient information is unavailable. In these methods, a fin…
A practical randomized trust-region method to escape saddle points in high dimension
Radu-Alexandru Dragomir, Xiaowen Jiang, Bonan Sun +1
Without randomization, escaping the saddle points of requires at least pieces of information about (values, gradients, Hessian-vec…
Consensus-Based Optimization Beyond Finite-Time Analysis
Pascal Bianchi, Radu-Alexandru Dragomir, Victor Priser
We analyze a zeroth-order particle algorithm for the global optimization of a non-convex function, focusing on a variant of Consensus-Based Optimization (CBO) with small but fixed…
A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
Etienne Boursier, Scott Pesme, Radu-Alexandru Dragomir
We study the dynamics of gradient flow with small weight decay on general training losses . Under mild regularity assumptions and assuming convergen…
Implicit Bias of Mirror Flow on Separable Data
Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion
We examine the continuous-time counterpart of mirror descent, namely mirror flow, on classification problems which are linearly separable. Such problems are minimised `at infinity'…
Convex quartic problems: homogenized gradient method and preconditioning
Radu-Alexandru Dragomir, Yurii Nesterov
We consider a convex minimization problem for which the objective is the sum of a homogeneous polynomial of degree four and a linear term. Such task arises as a subproblem in algor…