On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks

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.

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

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 ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

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 ...

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 ...

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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

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 ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

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. ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

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 ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

To retrieve Surface Solar Radiation (SSR) from satellite images, a baseline reflectance of the observed ground in clear-sky conditions, also called background reflectance, is necessary to distinguish atmospheric absorption and scattering effects from surfa ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

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 ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

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 ...

On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks

Chat with Graph Search

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning

Generalization of Scaled Deep ResNets in the Mean-Field Regime

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

Random matrix methods for high-dimensional machine learning models

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

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

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

Robust machine learning for neuroscientific inference

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

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

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

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

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

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context

Machine Learning for Modeling Stock Returns

Diffusion Stochastic Optimization for Min-Max Problems

Safe Deep Neural Networks

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