Publications related to Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections

Stability: a search for structure

In this thesis we study stability from several viewpoints. After covering the practical importance, the rich history and the ever-growing list of manifestations of stability, we study the following. (i) (Statistical identification of stable dynamical syste ...

EPFL2024

BENIGN LANDSCAPES OF LOW-DIMENSIONAL RELAXATIONS FOR ORTHOGONAL SYNCHRONIZATION ON GENERAL GRAPHS

Nicolas Boumal

Orthogonal group synchronization is the problem of estimating n elements Z(1),& mldr;,Z(n) from the rxr orthogonal group given some relative measurements R-ij approximate to Z(i)Z(j)(-1). The least-squares formulation is nonconvex. To avoid its local minim ...

Siam Publications2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Volkan Cevher, Fanghui Liu

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

2024

Efficient local linearity regularization to overcome catastrophic overfitting

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

2024

Towards Trustworthy Deep Learning for Image Reconstruction

Alexis Marie Frederic Goujon

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

EPFL2024

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

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Rachid Guerraoui, Nirupam Gupta, Rafaël Benjamin Pinot, Youssef Allouah, Geovani Rizk

The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogeneity however, which is the norm in practical scenarios, established lower bo ...

2023

Quantum circuits for solving local fermion-to-qubit map- pings

Giuseppe Carleo, Jannes Willy E. Nys

Local Hamiltonians of fermionic systems on a lattice can be mapped onto local qubit Hamiltonians. Maintaining the lo-cality of the operators comes at the ex-pense of increasing the Hilbert space with auxiliary degrees of freedom. In order to retrieve the l ...

VEREIN FORDERUNG OPEN ACCESS PUBLIZIERENS QUANTENWISSENSCHAF2023

Gaia Focused Product Release: Asteroid orbital solution: Properties and assessment

Stephan Morgenthaler, Shuangqing Liao

Context. We report the exploitation of a sample of Solar System observations based on data from the third Gaia Data Release (Gaia DR3) of nearly 157 000 asteroids. It extends the epoch astrometric solution over the time coverage planned for the Gaia DR4, w ...

Edp Sciences S A2023

Rapid motion estimation and correction using self-encoded FID navigators in 3D radial MRI

Tobias Kober, Davide Piccini

Purpose: To develop a self-navigated motion compensation strategy for 3D radial MRI that can compensate for continuous head motion by measuring rigid body motion parameters with high temporal resolution from the central k-space acquisition point (self-enco ...

Wiley2023

Self-correcting quantum many-body control using reinforcement learning with tensor networks

Friederike Metz

Quantum many-body control is a central milestone en route to harnessing quantum technologies. However, the exponential growth of the Hilbert space dimension with the number of qubits makes it challenging to classically simulate quantum many-body systems an ...

NATURE PORTFOLIO2023

Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks

Rahul Parhi

We study the problem of estimating an unknown function from noisy data using shallow ReLU neural networks. The estimators we study minimize the sum of squared data-fitting errors plus a regularization term proportional to the squared Euclidean norm of the ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

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

Regularization Techniques for Low-Resource Machine Translation

Alejandro Ramírez Atrio

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

EPFL2023

Data-driven Methods for Control: from Linear to Lifting

Yingzhao Lian

The progress towards intelligent systems and digitalization relies heavily on the use of automation technology. However, the growing diversity of control objects presents significant challenges for traditional control approaches, as they are highly depende ...

EPFL2023

Distributionally Robust Linear Quadratic Control

Daniel Kuhn, Cagil Kocyigit, Bahar Taskesen

Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It involves controlling a system with linear dynamics and imperfect observations ...

2023

(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability

Scott William Pesme, Nicolas Henri Bernard Flammarion, Mathieu Even

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and SGD with macroscop ...

2023

Iterative pre-conditioning for expediting the distributed gradient-descent method: The case of linear least-squares problem

Nirupam Gupta

This paper considers the multi-agent linear least-squares problem in a server-agent network architecture. The system comprises multiple agents, each with a set of local data points. The agents are connected to a server, and there is no inter-agent communic ...

PERGAMON-ELSEVIER SCIENCE LTD2022

A Least-Squares Method for the Solution of the Non-smooth Prescribed Jacobian Equation

Alexandre Caboussat, Dimitrios Gourzoulidis

We consider a least-squares/relaxation finite element method for the numerical solution of the prescribed Jacobian equation. We look for its solution via a least-squares approach. We introduce a relaxation algorithm that decouples this least-squares proble ...

SPRINGER/PLENUM PUBLISHERS2022