The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

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.

The rapid evolution of Machine Learning (ML) workloads, particularly Deep Neural Networks (DNNs) and Transformer-based models, has intensified demands on computing architectures, highlighting the limitations of traditional von Neumann systems due to the me ...

The nematode Caenorhabditis elegans offers a uniquely tractable model for studying the relationships between neuronal activity, connectivity, and behavior. Despite its simplicity, key questions remain about how information flows through its nervous system ...

In real-world speech data processing, the scarcity of annotated data and the abundance of unlabelled speech data present a significant challenge. To address this, we propose an efficient data selection pipeline for fine-tuning ASR models by generating pseu ...

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probab ...

Metal ions are indispensable cofactors for many proteins and play crucial roles in numerous biological processes, yet the computational design of metalloproteins and the optimization of metal coordination sites poses significant challenges due to the comp ...

While classical in many theoretical settings-and in particular in statistical physics-inspired works-the assumption of Gaussian i.i.d. input data is often perceived as a strong limitation in the context of statistics and machine learning. In this study, we ...

Multi-object spectroscopic galaxy surveys typically make use of photometric and colour criteria to select their targets. That is not the case of Euclid, which will use the NISP slitless spectrograph to record spectra for every source over its field of view ...

The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called workers). Beyond accuracy, the u ...

This dataset contains images (TIFF image data) of brain juvenile rats Wistar Han (P14) scanned immunostained slides by using an automated slide scanner (Olympus, VS120-L100, GER) equipped with a UPLSAPO 20x/0.75 air objective (Olympus, GER) and a Pike F5 ...

Studying the intricacies of individual subjects' moods and cognitive processing over extended periods of time presents a formidable challenge in medicine. While much of systems neuroscience appropriately focuses on the link between neural circuit functions ...

Intelligent Fault Diagnosis (IFD) based on deep learning has proven to be an effective and flexible solution, attracting extensive research. Deep neural networks can learn rich representations from vast amounts of representative labeled data for various ap ...

Over the last decades, implantable neural interfaces have been extensively explored and effectively deployed to address neurological and mental health disorders. The existing solutions present several limitations. Firstly, the physical size of the implanta ...

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

With the onset of large-scale astronomical surveys capturing millions of images, there is an increasing need to develop fast and accurate deconvolution algorithms that generalize well to different images. A powerful and accessible deconvolution method woul ...

Offshore wind farm modelling has been an area of rapidly increasing interest over the last two decades, with numerous analytical as well as computational-based approaches developed, in an attempt to produce designs that improve wind farm efficiency in powe ...

This study investigates the use of a low cost microphone combined with state-of-the-art machine learning (ML) algorithms as online process monitoring to differentiate various materials and process regimes of Laser-Powder Bed Fusion (LPBF). Three processing ...

Finding a reduction of complex, high-dimensional dynamics to its essential, low-dimensional "heart" remains a challenging yet necessary prerequisite for designing efficient numerical approaches. Machine learning methods have the potential to provide a gene ...

Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression wit ...

Loop closure detection helps simultaneous localization and mapping systems reduce map and state uncertainty via recognizing previously visited places along the path of a mobile robot. However, visual loop closure detection is susceptible to scenes with dyn ...

Curvilinear structures frequently appear in microscopy imaging as the object of interest. Crystallographic defects, i.e dislocations, are one of the curvilinear structures that have been repeatedly investigated under transmission electron microscopy (TEM) ...

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Chattez avec Graph Search

Stop Wasting your Cache! Bringing Machine Learning into Cache Computing

Behaviorally Relevant Information Content in Interneuron Activity

Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering

Global Group Fairness in Federated Learning via Function Tracking

Engineering of stable and functional metalloproteins using evolutionary computation, deep learning and simulation

Gaussian universality of perceptrons with random labels

Euclid: Testing photometric selection of emission-line galaxy targets?

Brief Announcement: A Case for Byzantine Machine Learning

Nissl_5, Raw images for Machine learning for histological annotation and quantification of cortical layers

Ethological computational psychiatry: Challenges and opportunities

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

Miniaturised, Wireless and Distributed Neural Interface Toward Cortical Visual Prosthesis

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Deep learning-based galaxy image deconvolution

Offshore wind farm wake modelling using deep feed forward neural networks for active yaw control and layout optimisation

Differentiation of materials and laser powder bed fusion processing regimes from airborne acoustic emission combined with machine learning

Discovery of Slow Variables in a Class Of Multiscale Stochastic Systems Via Neural Networks

Non-Structured DNN Weight Pruning--Is It Beneficial in Any Platform?

PlaceNet: A multi-scale semantic-aware model for visual loop closure detection

3D reconstruction of curvilinear structures with stereo matching deep convolutional neural networks