Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*

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.

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

We study the generalization of iterative noisy gradient schemes on smooth non-convex losses. Formally, we establish time-independent information theoretic generalization bounds for Stochastic Gradient Langevin Dynamics (SGLD) that do not diverge as the ite ...

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 ...

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 ...

Data-driven techniques are increasingly used to replace electronic-structure calculations of matter. In this context, a relevant question is whether machine learning (ML) should be applied directly to predict the desired properties or combined explicitly w ...

Introduction Since its emergence in late 2019, the SARS-CoV-2 virus has led to a global health crisis, affecting millions and reshaping societies and economies worldwide. Investigating the determinants of SARS-CoV-2 diffusion and their spatiotemporal dynam ...

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approache ...

Semi-discrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly non-discrete) probability measure, are believed to be computationally hard. Even though such problems are ubiquitous in statistics, ...

The problem of Byzantine resilience in distributed machine learning, a.k.a., Byzantine machine learning, consists in designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes, i.e., nodes with corrupt data or ...

Deep learning has achieved remarkable success in various challenging tasks such as generating images from natural language or engaging in lengthy conversations with humans. The success in practice stems from the ability to successfully train massive neural ...

Recent advances in ultrafast pump-probe spectroscopy provide access to hidden phases of correlated matter, including light-induced superconducting states. The theoretical understanding of these nonequilibrium phases remains limited, particularly for correl ...

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic d ...

Understanding the social context of eating is crucial for promoting healthy eating behaviors. Multimodal smartphone sensor data could provide valuable insights into eating behavior, particularly in mobile food diaries and mobile health apps. However, resea ...

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*

Chat with Graph Search

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Sequential Reasoning with Socially Caused Beliefs

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

A learning-based approach to stochastic optimal control under reach-avoid constraint

Learning to Reason with Neural Networks: Principles and Methods

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Generalization of Noisy SGD in Unbounded Non-convex Settings

On the Generalization of Stochastic Gradient Descent with Momentum

Understanding generalization and robustness in modern deep learning

Electronic Excited States from Physically Constrained Machine Learning

Environmental and geographical factors influencing the spread of SARS-CoV-2 over 2 years: a fine-scale spatiotemporal analysis

Asymptotics of feature learning in two-layer networks after one gradient-step

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution

Byzantine Machine Learning: A Primer

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

Twisted chiral superconductivity in photodoped frustrated Mott insulators

Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions

Understanding the Social Context of Eating with Multimodal Smartphone Sensing: The Role of Country Diversity