Universality laws for Gaussian mixtures in generalized linear models

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.

The ability of the brain to produce adaptive and dexterous movements relies on the seamless integration of sensory feedback into motor commands. Despite significant advances in motor neuroscience, critical gaps persist in understanding how proprioceptive a ...

Optimum groundwater management is important for addressing the global challenges of water scarcity, especially in arid regions. This study demonstrates the application of synthetic data combined with seismic methods to quantify water volumes in a controlle ...

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progre ...

Convolutional neural networks, as most artificial neural networks, are frequently viewed as methods different in essence from kernel-based methods. In this work we translate several classical convolutional neural networks into kernel-based counterparts. Ea ...

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

We consider a class of spreading processes on networks, which generalize commonly used epidemic models such as the SIR model or the SIS model with a bounded number of reinfections. We analyze the related problem of inference of the dynamics based on its pa ...

This thesis is devoted to the construction, analysis, and implementation of two types of hierarchical Markov Chain Monte Carlo (MCMC) methods for the solution of large-scale Bayesian Inverse Problems (BIP). The first hierarchical method we present is base ...

Event-driven acquisition uses neural-network-based recognition of specific biological events to trigger switching between slow and fast super-resolution imaging, enriching the capture of interesting events with high spatiotemporal resolution. A common goal ...

This thesis is centered on questions coming from Machine Learning (ML) and Statistical Field Theory (SFT). In Machine Learning, we consider the subfield of Supervised Learning (SL), and in particular regression tasks where one tries to find a regressor tha ...

Recently, a new adaptive path interpolation method has been developed as a simple and versatile scheme to calculate exactly the asymptotic mutual information of Bayesian inference problems defined on dense factor graphs. These include random linear and gen ...

Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of K Gaussians with generic means and covariances v ...

When a computational task tolerates a relaxation of its specification or when an algorithm tolerates the effects of noise in its execution, hardware, system software, and programming language compilers or their runtime systems can trade deviations from cor ...

A common pattern of progress in engineering has seen deep neural networks displacing human-designed logic. There are many advantages to this approach, divorcing decisionmaking from human oversight and intuition has costs as well. One is that deep neural ne ...

Universality laws for Gaussian mixtures in generalized linear models

Chat with Graph Search

Reverse engineering primate sensorimotor control with machine learning

Uncertainty quantification in groundwater volume predictions from seismic data using neural networks

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Learning Time-Scales in Two-Layers Neural Networks

Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods

The statistical complexity of early-stopped mirror descent

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Bayes-optimal inference for spreading processes on random networks

HIERARCHICAL MARKOV CHAIN MONTE CARLO METHODS FOR BAYESIAN INVERSE PROBLEMS

Event-driven acquisition for content-enriched microscopy

Complex Analysis meets Statistical Mechanics: Applications to Kernel Methods and Conformal Field Theory

Adaptive Path Interpolation Method for Sparse Systems: Application to a Censored Block Model

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions

Exploiting Errors for Efficiency: A Survey from Circuits to Applications

Exact Preimages of Neural Network Aircraft Collision Avoidance Systems