Wasserstein Adversarial Regularization for learning with label noise

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 ...

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 ...

Vision Transformers (ViTs) demonstrate remarkable performance in image classification through visual-token interaction learning, particularly when equipped with local information via region attention or convolutions. Although such architectures improve the ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

The minimization of a data-fidelity term and an additive regularization functional gives rise to a powerful framework for supervised learning. In this paper, we present a unifying regularization functional that depends on an operator L\documentclass[12pt]{ ...

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 ...

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 ...

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 ...

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

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 ...

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 ...

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 ...

Machine learning has become the state of the art for the solution of the diverse inverse problems arising from computer vision and medical imaging, e.g. denoising, super-resolution, de-blurring, reconstruction from scanner data, quantitative magnetic reson ...

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same envi ...

In network semi-supervised learning problems, only a subset of the network nodes is able to access the data labeling. This paper formulates a decentralized optimization problem where agents have individual decision rules to estimate, subject to the conditi ...

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning. However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

Wasserstein Adversarial Regularization for learning with label noise

Chat with Graph Search

Efficient local linearity regularization to overcome catastrophic overfitting

Understanding generalization and robustness in modern deep learning

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

AdaNCA: Neural Cellular Automata as Adaptors for More Robust Vision Transformer

Deep Learning Generalization with Limited and Noisy Labels

From Kernel Methods to Neural Networks: A Unifying Variational Formulation

Regularization Techniques for Low-Resource Machine Translation

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

A Neural-Network-Based Convex Regularizer for Inverse Problems

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

Robust Training and Verification of Deep Neural Networks

Regularization of polynomial networks for image recognition

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

Regularization of polynomial networks for image recognition

The statistical complexity of early-stopped mirror descent

Combining Model Driven and Data Driven Approaches for Inverse Problems in Parameter Estimation and Image Reconstruction: From Modelling to Validation

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Decentralized Semi-supervised Learning over Multitask Graphs

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks