activity
20242026
collaborators

22 papers

math.OC2026

A note on the complexity of random subspace model-based methods for derivative-free optimization

Coralia Cartis, Lindon Roberts

We demonstrate that, with a suitable rescaling, using Johnson-Lindenstrauss transforms (JLTs) in the random subspace model-based derivative-free optimization (DFO) algorithm from […

cs.LG2026

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

Joseph Webb, Sadok Jerad, Coralia Cartis

Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solv…

math.OC2026

Stochastic Krasnoselskii-Mann Iterations: Convergence without Uniformly Bounded Variance

Daniel Cortild, Coralia Cartis

We investigate the Stochastic Krasnoselskii-Mann iterations for expected nonexpansive fixed-point problems in a real Hilbert space. We establish convergence guarantees under signif…

cs.LG2026

Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees

Edward Tansley, Roy Makhlouf, Estelle Massart +1

Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the tra…

cs.LG2026

Quadratic Objective Perturbation: Curvature-Based Differential Privacy

Daniel Cortild, Coralia Cartis

Objective perturbation is a standard mechanism in differentially private empirical risk minimization. In particular, Linear Objective Perturbation (LOP) enforces privacy by adding…

math.OC2026

A Parameter-Free First-Order Algorithm for Non-Convex Optimization with Global Rate

Sichao Xiong, Sadok Jerad, Coralia Cartis

We introduce PF-AGD, the first parameter-free, deterministic, accelerated first-order method to achieve oracle complexity bound when minimizing sufficientl…