Publications associées à Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Scott William Pesme, Nicolas Henri Bernard Flammarion, Hristo Georgiev Papazov

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

On the Generalization of Stochastic Gradient Descent with Momentum

Volkan Cevher, Kimon Antonakopoulos

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Microtome Publishing2024

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

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

Data Downloaded via Parachute from a NASA Super-Pressure Balloon

Richard Massey, David Richard Harvey, Mathilde Jauzac, Lun Li

In April 2023, the superBIT telescope was lifted to the Earth's stratosphere by a helium-filled super-pressure balloon to acquire astronomical imaging from above (99.5% of) the Earth's atmosphere. It was launched from New Zealand and then, for 40 days, cir ...

MDPI2023

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

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

A Study on Gradient-based Meta-learning for Robust Deep Digital Twins

Olga Fink, Raffael Pascal Theiler, Michele Viscione

Deep-learning-based digital twins (DDT) are a promising tool for data-driven system health management because they can be trained directly on operational data. A major challenge for efficient training however is that industrial datasets remain unlabeled. T ...

Research Publishing2023

Data-Driven Control and Optimization under Noisy and Uncertain Conditions

Baiwei Guo

Control systems operating in real-world environments often face disturbances arising from measurement noise and model mismatch. These factors can significantly impact the perfor- mance and safety of the system. In this thesis, we aim to leverage data to de ...

EPFL2023

Safe Zeroth-Order Convex Optimization Using Quadratic Local Approximations

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

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

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function

Patrick Thiran, Saber Salehkaleybar, Negar Kiyavash

We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property with

1\le\alpha\le2

which holds in a wide range of applications in machine learning and signal processing. This conditio ...

NeurIPS2022

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

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Volkan Cevher, Alp Yurtsever, Maria-Luiza Vladarean

We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully inc ...

2022

Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation

Sundar Subramaniam Ganesh

This work aims to study the effects of wind uncertainties in civil engineering structural design. Optimising the design of a structure for safety or operability without factoring in these uncertainties can result in a design that is not robust to these per ...

EPFL2022

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Angelos Katharopoulos

Deep neural networks have completely revolutionized the field of machine learning by achieving state-of-the-art results on various tasks ranging from computer vision to protein folding. However, their application is hindered by their large computational an ...

EPFL2022

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Volkan Cevher, Ali Kavis, Leello Tadesse Dadi, Efstratios Panteleimon Skoulakis, Kimon Antonakopoulos

We propose an adaptive variance-reduction method, called AdaSpider, for minimization of L-smooth, non-convex functions with a finite-sum structure. In essence, AdaSpider combines an AdaGrad-inspired [Duchi et al., 2011, McMahan & Streeter, 2010], but a fai ...

2022

Level-set-based Shape Optimization on Soft Magnetic Composites with Isotropy Constraint

Yves Perriard, Adrien Jean-Michel Thabuis, Xiaotao Ren

Soft Magnetic Composites (SMCs) demonstrate excellent potentials for electromagnetic applications. The isotropy is one critical feature in designing the composite. This work presents a shape optimization algorithm for SMCs subject to isotropy and volume co ...

Institute of Electrical and Electronics Engineers2022

On The Convergence Of Stochastic Primal-Dual Hybrid Gradient

Volkan Cevher, Ahmet Alacaoglu

In this paper, we analyze the recently proposed stochastic primal-dual hybrid gradient (SPDHG) algorithm and provide new theoretical results. In particular, we prove almost sure convergence of the iterates to a solution with convexity and linear convergenc ...

SIAM PUBLICATIONS2022

Momentum-Based Policy Gradient with Second-Order Information

Patrick Thiran, Saber Salehkaleybar, Negar Kiyavash, Mohammadsadegh Khorasani

Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose a variance-reduced policy-gradient m ...

2022

Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond

Ahmet Alacaoglu

Stochastic gradient descent (SGD) and randomized coordinate descent (RCD) are two of the workhorses for training modern automated decision systems. Intriguingly, convergence properties of these methods are not well-established as we move away from the spec ...

EPFL2021