Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks

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 first two chapters develop ML-based models that generate conditional SDF estimates efficiently using conditioning information sets, resulting in minimal pricing errors and superior Sharpe ratios compared to traditional conditional asset pricing models. ...

This paper introduces a novel architecture for Quantum Graph Neural Networks, which is significantly different from previous approaches found in the literature. The proposed approach produces similar outcomes with respect to previous models but with fewer ...

BackgroundBronchiolitis Obliterans Syndrome (BOS), a fibrotic airway disease that may develop after lung transplantation, conventionally relies on pulmonary function tests (PFTs) for diagnosis due to limitations of CT imaging. Deep neural networks (DNNs) h ...

More attention has been paid to integrating existing knowledge with data to understand the complex mechanical behaviour of geomaterials, but it incurs scepticism and criticism on its generalizability and robustness. Moreover, a common mistake in current da ...

Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices ...

Monitoring of cardiac output (CO) is a mainstay of hemodynamic management in the acutely or critically ill patient. Invasive determination of CO using thermodilution, albeit regarded as the gold standard, is cumbersome and bears risks inherent to catheteri ...

As the demand for high channel counts and high-resolution recordings of neural activity continues to grow, the increased power and data rate generated impose hard constraints on the telemetry capabilities of wireless implantable neural interfaces. To addre ...

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(ϵ-2) to achieve an ϵ-stationary solut ...

Magnons are the quanta of spin waves and transport angular momenta through magnetically ordered materials. They can be used to distribute and control on-chip GHz signals without charge flow, thereby avoiding Joule heating. Beyond multiplexed signal process ...

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high ...

Scientific Machine Learning (SciML) is a recently emerged research field which combines physics-based and data-driven models for the numerical approximation of differential problems. Physics-based models rely on the physical understanding of the problem at ...

The Birman-Williams theorem gives a connection between the collection of unstable periodic orbits (UPOs) contained within a chaotic attractor and the topology of that attractor, for three-dimensional systems. In certain cases, the fractal dimension of a ch ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

Noise in the data is one of the main cause of model performance drop. Denoising is therefore a critical step in most data pipelines. In this paper we propose to fuse the learning abilities of Neural Network with the well-proven efficiency of the wavelet pa ...

This paper proposes a novel learning-based approach for achieving exponential stabilization of nonlinear control-affine systems. We leverage the Control Contraction Metrics (CCMs) framework to co-synthesize Neural Contraction Metrics (NCMs) and Neural Netw ...

Smart meters, devices measuring the electricity and gas consumption of a household, are currently being deployed at a fast rate throughout the world. The data they collect are extremely useful, including in the fight against climate change. However, these ...

A data-driven inverse design method based on neural networks is proposed for turbomachinery. In the devised methodology, design parameters are provided as input to the neural network, and performance attributes, e.g. efficiency, as output. Once trained, th ...

We investigate the learning of a convex patch-based synthesis model for the reconstruction of images. In essence, we propose to learn a dictionary via bilevel optimization for denoising. Using implicit differentiation, we find a closed-form formula of the ...

Computational chemistry techniques offer tremendous potential for accelerating the discovery of sustainable chemical processes and reactions. However, the environmental impacts of the substantial computing power required for these digital methods are often ...

In this paper, we present EdgeFace - a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achi ...

Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks

Chattez avec Graph Search

Machine Learning Applications to Conditional Asset Pricing: Attention, CNNs, and Neural Tangent Kernels

A Study on Quantum Graph Neural Networks Applied to Molecular Physics

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT

t-PiNet: A thermodynamics-informed hierarchical learning for discovering constitutive relations of geomaterials

Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator

Machine learning-enabled estimation of cardiac output from peripheral waveforms is independent of blood pressure measurement location in an in silico population

A Reconfigurable High-Dynamic Range ∆Σ Front-End with Event-Based Decimation for Bandwidth-Efficient Implantable Neural Interfaces

Diffusion Stochastic Optimization for Min-Max Problems

Perspective on nonvolatile magnon-signal storage and in-memory computation for low-power consuming magnonics

Enhancing skin lesion classification: a CNN approach with human baseline comparison

Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning

The topology of a chaotic attractor in the Kuramoto-Sivashinsky equation

On the added value of sequential deep learning for the upscaling of evapotranspiration

Robust time series denoising with learnable wavelet packet transform

Neural Exponential Stabilization of Control-affine Nonlinear Systems

Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks

DATA-DRIVEN INVERSE DESIGN METHOD FOR TURBOMACHINERY

Learning a Convex Patch-Based Synthesis Model via Deep Equilibrium

Balancing computational chemistry's potential with its environmental impact

EdgeFace: Efficient Face Recognition Model for Edge Devices