Publications related to Stochastic gradient descent

Toward plasma drifts in EMC3: Implementation of gradient, divergence, and particle tracing schemes

This paper presents a first implementation of gradient, divergence, and particle tracing schemes for the EMC3 code, a stochastic 3D plasma fluid code widely employed for edge plasma and impurity transport modeling in tokamaks and stellarators. These scheme ...

Weinheim2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Marco Picasso, Alexandre Caboussat, Maude Girardin

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Lausanne2024

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Nirupam Gupta

In this article, we study the problem of Byzantine fault-tolerance in a federated optimization setting, where there is a group of agents communicating with a centralized coordinator. We allow up to

f

Byzantine-faulty agents, which may not follow a prescr ...

Piscataway2023

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

Data Downloaded via Parachute from a NASA Super-Pressure Balloon

David Richard Harvey, Mathilde Jauzac, Richard Massey, 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 ...

Basel2023

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

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Yulun Jiang, Chen Liu, Zhuoyi Huang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023

Robust Collaborative Learning with Linear Gradient Overhead

Rachid Guerraoui, Nirupam Gupta, John Stephan, Sadegh Farhadkhani, Le Nguyen Hoang, Rafaël Benjamin Pinot

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

PLMR2023

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Nirupam Gupta, Shuo Liu

This paper considers the problem of resilient distributed optimization and stochastic learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has its own local cost function. The agents collaborate with ...

New York2023

Stochastic gradient descent

Graph Chatbot

Chat with Graph Search

Toward plasma drifts in EMC3: Implementation of gradient, divergence, and particle tracing schemes

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Universal and adaptive methods for robust stochastic optimization

Data Downloaded via Parachute from a NASA Super-Pressure Balloon

Phenomenological theory of variational quantum ground-state preparation

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Robust Collaborative Learning with Linear Gradient Overhead

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Toward plasma drifts in EMC3: Implementation of gradient, divergence, and particle tracing schemes

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Universal and adaptive methods for robust stochastic optimization

Robust Collaborative Learning with Linear Gradient Overhead

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Data Downloaded via Parachute from a NASA Super-Pressure Balloon

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Phenomenological theory of variational quantum ground-state preparation