Publications related to Hyperparameter (machine learning)

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

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

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

Text Representation Learning for Low Cost Natural Language Understanding

Jan Frederik Jonas Florian Mai

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

EPFL2023

On the symmetries in the dynamics of wide two-layer neural networks

Lénaïc Chizat

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a general class of s ...

AMER INST MATHEMATICAL SCIENCES-AIMS2023

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

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

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Olga Fink, Vinay Sharma, Manav Manav

We propose a physics-informed message-passing graph neural network (GNN) for learning the dynamics of springmass systems. The proposed method embeds the underlying physics directly into the message-passing scheme of the GNN. We compare the new scheme with ...

Research Publishing2023

Short-term runoff forecasting in an alpine catchment with a long short-term memory neural network

Devis Tuia, Marc Conrad Russwurm, Corinna Barbara Frank

The governing hydrological processes are expected to shift under climate change in the alpine regions of Switzerland. This raises the need for more adaptive and accurate methods to estimate river flow. In high-altitude catchments influenced by snow and gla ...

2023

Privacy-preserving federated neural network training and inference

Sinem Sav

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data silos. Sharing, transferring, and centralizing the data from silos, however, is difficult due to current privacy regulations (e.g., H ...

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

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Giuseppe Carleo

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

SCIPOST FOUNDATION2022

Hyperparameter (machine learning)

Graph Chatbot

Chat with Graph Search

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Text Representation Learning for Low Cost Natural Language Understanding

On the symmetries in the dynamics of wide two-layer neural networks

Phenomenological theory of variational quantum ground-state preparation

Deep Learning Generalization with Limited and Noisy Labels

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Short-term runoff forecasting in an alpine catchment with a long short-term memory neural network

Privacy-preserving federated neural network training and inference

Regularization Techniques for Low-Resource Machine Translation

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Deep Learning Generalization with Limited and Noisy Labels

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Privacy-preserving federated neural network training and inference

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Phenomenological theory of variational quantum ground-state preparation

On the symmetries in the dynamics of wide two-layer neural networks

Regularization Techniques for Low-Resource Machine Translation

Text Representation Learning for Low Cost Natural Language Understanding

Short-term runoff forecasting in an alpine catchment with a long short-term memory neural network

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states