Dictionary Identifiability from Few Training Samples

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.

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Electroencephalography (EEG) data entail a complex spatiotemporal structure that reflects ongoing organi-zation of brain activity. Characterization of the spatial patterns is an indispensable step in numerous EEG processing pipelines. We present a novel me ...

In this paper, we set the mathematical foundations of the Dynamical Low-Rank Approximation (DLRA) method for stochastic differential equations (SDEs). DLRA aims at approximating the solution as a linear combination of a small number of basis vectors with r ...

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and req ...

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Single-photon 3D cameras can record the time-of-arrival of billions of photons per second with picosecond accuracy. One common approach to summarize the photon data stream is to build a per-pixel timestamp histogram, resulting in a 3D histogram tensor that ...

The Transfer Matrix formalism is ubiquitous when it comes to study wave propagation in various stratified media, applications ranging from Seismology to Quantum Mechanics. A relation between variables at two points in two different layers can be establishe ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Data-driven schemes that associate molecular and crystal structures with their microscopic properties share the need for a concise, effective description of the arrangement of their atomic constituents. Many types of models rely on descriptions of atom-cen ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

This work is concerned with approximating matrix functions for banded matrices, hierarchically semiseparable matrices, and related structures. We develop a new divide-and-conquer method based on (rational) Krylov subspace methods for performing low-rank up ...

Sign Language conveys information through multiple channels composed of manual (handshape, hand movement) and non-manual (facial expression, mouthing, body posture) components. Sign language assessment involves giving granular feedback to a learner, in ter ...

We consider increasingly complex models of matrix denoising and dictionary learning in the Bayes-optimal setting, in the challenging regime where the matrices to infer have a rank growing linearly with the system size. This is in contrast with most existin ...

The input of almost every machine learning algorithm targeting the properties of matter at the atomic scale involves a transformation of the list of Cartesian atomic coordinates into a more symmetric representation. Many of the most popular representations ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

“You never forget how to ride a bike”, – but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other skills in between, and still retrieve the original knowledge when necessary. The mechanisms of this capab ...

Background Coercion in psychiatry is a controversial issue. Identifying its predictors and their interaction using traditional statistical methods is difficult, given the large number of variables involved. The purpose of this study was to use machine-lear ...

Dictionary Identifiability from Few Training Samples

Chat with Graph Search

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

Dynamical Low-Rank Approximation for Stochastic Differential Equations

Self-supervised and few-shot learning for robust bioaerosol monitoring

Domain shift, domain adaptation, and generalization: A focus on MRI

Learned Compressive Representations for Single-Photon 3D Imaging

Harmonic decomposition of the trace of 1D transfer matrices in layered media

Learning to Assemble with Alternative Plans

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Unified theory of atom-centered representations and message-passing machine-learning schemes

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

DIVIDE-AND-CONQUER METHODS FOR FUNCTIONS OF MATRICES WITH BANDED OR HIERARCHICAL LOW-RANK STRUCTURE\ast

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment

Statistical limits of dictionary learning: Random matrix theory and the spectral replica method

Optimal radial basis for density-based atomic representations

Improving the accuracy and interpretability of neural networks for wind power forecasting

Context selectivity with dynamic availability enables lifelong continual learning

Predicting involuntary hospitalization in psychiatry: A machine learning investigation