Publications associées à Certification Aspects of the Fast Gradient Method for Solving the Dual of Parametric Convex Programs

Publications associées (32)

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

2025

Randomized low-rank approximation of parameter-dependent matrices

Daniel Kressner, Hei Yin Lam

This work considers the low-rank approximation of a matrix (Formula presented.) depending on a parameter (Formula presented.) in a compact set (Formula presented.). Application areas that give rise to such problems include computational statistics and dyna ...

2024

Randomized flexible GMRES with deflated restarting

Laura Grigori

For a high-dimensional problem, a randomized Gram-Schmidt (RGS) algorithm is beneficial in terms of both computational cost and numerical stability. We apply this dimension reduction technique by random sketching to Krylov subspace methods, e.g., to the ge ...

Springer2024

Scalable constrained optimization

Maria-Luiza Vladarean

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

EPFL2024

On distributional autoregression and iterated transportation

Victor Panaretos, Laya Ghodrati

We consider the problem of defining and fitting models of autoregressive time series of probability distributions on a compact interval of Double-struck capital R. An order-1 autoregressive model in this context is to be understood as a Markov chain, where ...

Wiley2024

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Anastasiia Koloskova

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Paul Scharnhorst

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

EPFL2024

A Combination Technique for Optimal Control Problems Constrained by Random PDEs

Fabio Nobile, Tommaso Vanzan

We present a combination technique based on mixed differences of both spatial approximations and quadrature formulae for the stochastic variables to solve efficiently a class of optimal control problems (OCPs) constrained by random partial differential equ ...

2024

Residual-based attention in physics-informed neural networks

Nikolaos Stergiopoulos, Sokratis Anagnostopoulos

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Elsevier Science Sa2024

Universal and adaptive methods for robust stochastic optimization

Ali Kavis

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

EPFL2023

Distributional Regression and Autoregression via Optimal Transport

Laya Ghodrati

We present a framework for performing regression when both covariate and response are probability distributions on a compact and convex subset of

\R^d

. Our regression model is based on the theory of optimal transport and links the conditional Fr'echet m ...

EPFL2023

A multigrid method for PDE-constrained optimization with uncertain inputs

Fabio Nobile, Tommaso Vanzan

In this manuscript, we present a collective multigrid algorithm to solve efficiently the large saddle-point systems of equations that typically arise in PDE-constrained optimization under uncertainty, and develop a novel convergence analysis of collective ...

Springer Science and Business Media LLC2024

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Volkan Cevher, Thomas Michaelsen Pethick, Wanyun Xie

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

2023

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Mehmet Fatih Sahin

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

EPFL2023

NbN films with high kinetic inductance for high-quality compact superconducting resonators

Edoardo Charbon, Pasquale Scarlino, Fabrizio Minganti, Simone Frasca, Marco Scigliuzzo, Fabian Oppliger, Vincent Jean Yves Jouanny

Niobium nitride (NbN) is a particularly promising material for quantum technology applications, as it shows the degree of reproducibility necessary for large-scale superconducting circuits. We demonstrate that resonators based on NbN thin films present a o ...

American Physical Society (APS)2023

Safe Zeroth-Order Convex Optimization Using Quadratic Local Approximations

Giancarlo Ferrari Trecate, Yuning Jiang, Maryam Kamgarpour, Baiwei Guo

We address black-box convex optimization problems, where the objective and constraint functions are not explicitly known but can be sampled within the feasible set. The challenge is thus to generate a sequence of feasible points converging towards an optim ...

IEEE2023

Training Efficient Controllers via Analytic Policy Gradient

Dario Floreano, Davide Scaramuzza, Valentin Wüest

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but requir ...

New York2023

Learning ground states of gapped quantum Hamiltonians with Kernel Methods

Giuseppe Carleo, Filippo Vicentini, Riccardo Rossi, Clemens Giuliani

Neural network approaches to approximate the ground state of quantum hamiltonians require the numerical solution of a highly nonlinear optimization problem. We introduce a statistical learning approach that makes the optimization trivial by using kernel me ...

Verein Forderung Open Access Publizierens Quantenwissenschaf2023

Hardware-Software Co-design for Improved Resource Utilization in DNN Accelerators

Ahmet Caner Yüzügüler

Deep neural networks (DNN) have become an essential tool to tackle challenging tasks in many fields of computer science. However, their high computational complexity limits their applicability. Specialized DNN accelerators have been developed to accommodat ...

EPFL2023

Preconditioning techniques for generalized Sylvester matrix equations

Yannis Dirk Voet

Sylvester matrix equations are ubiquitous in scientific computing. However, few solution techniques exist for their generalized multiterm version, as they now arise in an increasingly large number of applications. In this work, we consider algebraic parame ...

2023