22 papers
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 […
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…
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…
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…
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…
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…