Total Variation Regularization of Shape Signals

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.

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

This paper introduces a novel method for data-driven robust control of nonlinear systems based on the Koopman operator, utilizing Integral Quadratic Constraints (IQCs). The Koopman operator theory facilitates the linear representation of nonlinear system d ...

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 ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

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 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 ...

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

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 ...

This paper considers the problem of second-degree price discrimination when the type distribution is unknown or imperfectly specified by means of an ambiguity set. As robustness measure we use a performance index, equivalent to relative regret, which quant ...

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 ...

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 ...

The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in quality. Unfortunately, these new methods often lack reliability and explainability, and there is a growing interest to address these ...

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

Factored form is a powerful multi-level representation of a Boolean function that readily translates into an implementation of the function in CMOS technology. In particular, the number of literals in a factored form correlates strongly with the number of ...

Description (through texts, images, models or samples) played a central role in the patent regimes that emerged in the eighteenth century, first in England, later in the United States and in France. Description ensured that the contract—protection in excha ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

Cyclopentadienyl (Cp) metal complexes and their chiral counterparts (CpX) have enabled the development of challenging C-H activation transformations. While major progresses were made in developing new chiral CpX complexes and exploring their reactivity, th ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Total Variation Regularization of Shape Signals

Chat with Graph Search

Efficient local linearity regularization to overcome catastrophic overfitting

Koopman-based Data-driven Robust Control of Nonlinear Systems Using Integral Quadratic Constraints

Aggregating Spatial and Photometric Context for Photometric Stereo

Towards Trustworthy Deep Learning for Image Reconstruction

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Understanding generalization and robustness in modern deep learning

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

Neural Distributed Image Compression with Cross-Attention Feature Alignment

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

Price Discrimination with Robust Beliefs

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

Regularization of polynomial networks for image recognition

Regularization of polynomial networks for image recognition

A Neural-Network-Based Convex Regularizer for Inverse Problems

Regularization Techniques for Low-Resource Machine Translation

Improving Standard-Cell Design Flow using Factored Form Optimization

Writing and Drawing Inventions: Patents and Technology in France and the United States (18th-19th centuries)

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Complexation Strategies towards Challenging Group 9 Metal Cyclopentadienyl Scaffolds

Improving Generalization of Pretrained Language Models