Publications related to Local SGD Converges Fast and Communicates Little

Understanding generalization and robustness in modern deep learning

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

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 ...

Brookline2024

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

Phenomenological theory of variational quantum ground-state preparation

Ivano Tavernelli, Giuseppe Carleo

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

College Pk2023

Communication-efficient distributed training of machine learning models

Thijs Vogels

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

EPFL2023

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

Masked Training of Neural Networks with Partial Gradients

Martin Jaggi, Sebastian Urban Stich, Amirkeivan Mohtashami

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extra-gradient), limiting SGD updates to a sub ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Florent Gérard Krzakala, Lenka Zdeborová, Ludovic Théo Stephan, Bruno Loureiro

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically different for narrow net-works, which tend to get stuck in badly-generalizing loca ...

2022

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

Patrick Thiran, Negar Kiyavash, Saber Salehkaleybar

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

Towards Understanding Sharpness-Aware Minimization

Nicolas Henri Bernard Flammarion, Maksym Andriushchenko

Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations which significantly improves generalization in various settings. We argue that the existing justifications for the success of SAM which are based ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Local SGD Converges Fast and Communicates Little

Graph Chatbot

Chat with Graph Search

Understanding generalization and robustness in modern deep learning

On the Generalization of Stochastic Gradient Descent with Momentum

Deep Learning Generalization with Limited and Noisy Labels

Phenomenological theory of variational quantum ground-state preparation

Communication-efficient distributed training of machine learning models

Universal and adaptive methods for robust stochastic optimization

Masked Training of Neural Networks with Partial Gradients

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

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

Towards Understanding Sharpness-Aware Minimization

Understanding generalization and robustness in modern deep learning

Phenomenological theory of variational quantum ground-state preparation

On the Generalization of Stochastic Gradient Descent with Momentum

Deep Learning Generalization with Limited and Noisy Labels

Communication-efficient distributed training of machine learning models

Universal and adaptive methods for robust stochastic optimization

Masked Training of Neural Networks with Partial Gradients

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Towards Understanding Sharpness-Aware Minimization

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