Sparsistency of $\ell_1$-Regularized $M$-Estimators

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.

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging w ...

Atomic simulations using machine learning interatomic potential (MLIP) have gained a lot of popularity owing to their accuracy in comparison to conventional empirical potentials. However, the transferability of MLIP to systems outside the training set pose ...

This article presents the outcomes of a large project towards the investigation of the lateral performance of full-scale industrialized light-frame wooden diaphragms. 10 full-scale diaphragms of 3.6 m by 2.4 m were tested under in-plane lateral loading (mo ...

Higher-order asymptotics provide accurate approximations for use in parametric statistical modelling. In this thesis, we investigate using higher-order approximations in two-specific settings, with a particular emphasis on the tangent exponential model. ...

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 ...

The log law of the wall, joining the inner, near-wall mean velocity profile (MVP) in wall-bounded turbulent flows to the outer region, has been a permanent fixture of turbulence research for over hundred years, but there is still no general agreement on th ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

Outliers in discrete choice response data may result from misclassification and misreporting of the response variable and from choice behaviour that is inconsistent with modelling assumptions (e.g. random utility maximisation). In the presence of outliers, ...

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and SGD with macroscop ...

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 ...

Photoplethysmography (PPG) is a widely emerging method to assess vascular health in humans. The origins of the signal of reflective PPG on peripheral arteries have not been thoroughly investigated. We aimed to identify and quantify the optical and biomecha ...

Sparsistency of $\ell_1$-Regularized $M$-Estimators

Chat with Graph Search

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Comparing transferability in neural network approaches and linear models for machine-learning interaction potentials

Testing and nonlinear modelling of industrialized light-frame wooden diaphragms including optimized nailing and nonstructural sheathing

Higher Order Asymptotics: Applications to Satellite Conjunction and Boundary Problems

Dynamical Low-Rank Approximation for Stochastic Differential Equations

The hunt for the Karman 'constant' revisited

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Robust discrete choice models with t-distributed kernel errors

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Robust Collaborative Learning with Linear Gradient Overhead

Regularization of polynomial networks for image recognition

(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability

The statistical complexity of early-stopped mirror descent

Quantification of the Phenomena Affecting Reflective Arterial Photoplethysmography