Asymptotics of feature learning in two-layer networks after one gradient-step

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

Cyclic peptides are attractive for drug discovery due to their excellent binding properties and the potential to cross cell membranes. However, by far not all cyclic peptides are cell permeable, and measuring or predicting their membrane permeability is no ...

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 ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Asymptotics of feature learning in two-layer networks after one gradient-step

Chattez avec Graph Search

Person Re-Identification and its Application to Multi-Object Tracking

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

A learning-based approach to stochastic optimal control under reach-avoid constraint

Bulk measurement of membrane permeability for random cyclic peptides in living cells to guide drug development

Understanding generalization and robustness in modern deep learning

On the Generalization of Stochastic Gradient Descent with Momentum

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes