Mean-Field methods for Structured Deep-Learning in Computer Vision

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In real-world speech data processing, the scarcity of annotated data and the abundance of unlabelled speech data present a significant challenge. To address this, we propose an efficient data selection pipeline for fine-tuning ASR models by generating pseu ...

The rapid evolution of Machine Learning (ML) workloads, particularly Deep Neural Networks (DNNs) and Transformer-based models, has intensified demands on computing architectures, highlighting the limitations of traditional von Neumann systems due to the me ...

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probab ...

This paper introduces a distributed operational solution for integrated transmission-distribution (ITD) system management. A fundamental challenge in designing distributed approaches for AC optimal power flow (OPF) problems in ITD systems is the nonconvexi ...

The nematode Caenorhabditis elegans offers a uniquely tractable model for studying the relationships between neuronal activity, connectivity, and behavior. Despite its simplicity, key questions remain about how information flows through its nervous system ...

Metal ions are indispensable cofactors for many proteins and play crucial roles in numerous biological processes, yet the computational design of metalloproteins and the optimization of metal coordination sites poses significant challenges due to the comp ...

The parameters for determining the economic order quantity (EOQ) are often not well known or may change between order cycles in an unpredictable manner. We propose a distribution-free method to determine a relatively robust EOQ that guarantees optimal cost ...

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 ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

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 ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

While classical in many theoretical settings-and in particular in statistical physics-inspired works-the assumption of Gaussian i.i.d. input data is often perceived as a strong limitation in the context of statistics and machine learning. In this study, we ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

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 ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

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 ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches multiple times and show that it significantly changes the conclusion about wh ...

Mean-Field methods for Structured Deep-Learning in Computer Vision

Chat with Graph Search

Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering

Stop Wasting your Cache! Bringing Machine Learning into Cache Computing

Global Group Fairness in Federated Learning via Function Tracking

Advancing Distributed AC Optimal Power Flow for Integrated Transmission-Distribution Systems

Behaviorally Relevant Information Content in Interneuron Activity

Engineering of stable and functional metalloproteins using evolutionary computation, deep learning and simulation

Relatively Robust Economic Order Quantity with Optimal Laplacian Confidence Intervals

Understanding generalization and robustness in modern deep learning

Random matrix methods for high-dimensional machine learning models

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Gaussian universality of perceptrons with random labels

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

On the Generalization of Stochastic Gradient Descent with Momentum

Aggregating Spatial and Photometric Context for Photometric Stereo

Meta-learning to address diverse Earth observation problems across resolutions

Robust machine learning for neuroscientific inference

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Topics in statistical physics of high-dimensional machine learning

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents