Network Loss Inference with Second Order Statistics of End-to-End Flows

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.

In the rapidly evolving AI era with large language models (LLMs) at the core, making LLMs more trustworthy and efficient, especially in output generation (inference), has gained significant attention. This is to reduce plausible but faulty LLM outputs (a.k ...

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 ...

Type inference in the presence of first-class or "impredicative" second-order polymorphism a la System F has been an active research area for several decades, with original works dating back to the end of the 80s. Yet, until now many basic problems remain ...

Negative interest rate regimes typically involve reserve tiering to exempt a portion of bank reserves from negative rates. We study the effects on bank behavior of a large and unanticipated change in reserve tiering by the Swiss National Bank that generate ...

Zoning reform is a crucial tool for cities to adapt to contemporary challenges. However, its implementation remains challenging. Property owners, with a vested interest in the value of their neighborhoods, are sensitive to local developments and the potent ...

We present an extended validation of semi-analytical, semi-empirical covariance matrices for the two-point correlation function (2PCF) on simulated catalogs representative of luminous red galaxies (LRGs) data collected during the initial 2 months of operat ...

Recent cosmic shear studies have shown that higher-order statistics (HOS) developed by independent teams now outperform standard two-point estimators in terms of statistical precision thanks to their sensitivity to the non-Gaussian features of large-scale ...

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a general class of s ...

Context. We present a novel approach to the construction of mock galaxy catalogues for large-scale structure analysis based on the distribution of dark matter halos obtained with effective bias models at the field level. Aims. We aim to produce mock galaxy ...

Universal inference enables the construction of confidence intervals and tests without regularity conditions by splitting the data into two parts and appealing to Markov's inequality. Previous investigations have shown that the cost of this generality is a ...

We develop a methodology to measure the expected loss of commercial banks in a market downturn, which we call stressed expected loss (SEL). We simulate a market downturn as a negative shock on interest rate and credit market risk factors that reflect the b ...

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in orde ...

Dark Energy Spectroscopic Instrument (DESI) will construct a large and precise three-dimensional map of our Universe. The survey effective volume reaches similar to 20 h(-3) Gpc(3). It is a great challenge to prepare high-resolution simulations with a much ...

Contact tracing is an essential tool to mitigate the impact of a pandemic, such as the COVID-19 pandemic. In order to achieve efficient and scalable contact tracing in real time, digital devices can play an important role. While a lot of attention has been ...

Efficient sampling of complex high-dimensional probability distributions is a central task in computational science. Machine learning methods like autoregressive neural networks, used with Markov chain Monte Carlo sampling, provide good approximations to s ...

Recent years have witnessed a rise in real-world data captured with rich structural information that can be better depicted by multi-relational or heterogeneous graphs. However, research on relational representation learning has so far mostly focused on th ...

Aims. We investigate the contribution of shot-noise and sample variance to uncertainties in the cosmological parameter constraints inferred from cluster number counts, in the context of the Euclid survey. ...

This thesis empirically explored the impacts of IT investment on three different scenarios under the common denominator / threads of IT investments. It comprises three different essays on the impacts of IT investments. IT investments and its impact on many ...

Quantifying tensions - inconsistencies amongst measurements of cosmological parameters by different experiments - has emerged as a crucial part of modern cosmological data analysis. Statistically significant tensions between two experiments or cosmological ...

Linear inverse problems are ubiquitous. Often the measurements do not follow a Gaussian distribution. Additionally, a model matrix with a large condition number can complicate the problem further by making it ill-posed. In this case, the performance of pop ...

Network Loss Inference with Second Order Statistics of End-to-End Flows

Chattez avec Graph Search

Trustworthy and Efficient LLMs Meet Databases

Random matrix methods for high-dimensional machine learning models

When Subtyping Constraints Liberate A Novel Type Inference Approach for First-Class Polymorphism

Tiers of joy? Reserve tiering and bank behavior in a negative-rate environment

Spatial Modeling for Building Design Evaluation: from Visual Landscape Quality Assessment to Devaluation Risk Estimation

Validation of semi-analytical, semi-empirical covariance matrices for two-point correlation function for early DESI data

Euclid preparation: XXVIII. Forecasts for ten different higher-order weak lensing statistics

On the symmetries in the dynamics of wide two-layer neural networks

DESI mock challenge Halo and galaxy catalogues with the bias assignment method

A note on universal inference

Predicting the stressed expected loss of large US banks

Stochastic distributed learning with gradient quantization and double-variance reduction

The DESI N-body Simulation Project - II. Suppressing sample variance with fast simulations

Epidemic mitigation by statistical inference from contact tracing data

Unbiased Monte Carlo cluster updates with autoregressive neural networks

Representation Learning for Multi-relational Data

Euclid : Effects of sample covariance on the number counts of galaxy clusters

IT Investment and its impacts : does IT matter during crisis, during financing and in Innovation?

Assessing tension metrics with dark energy survey and Planck data

The regularized tau estimator: A robust and efficient solution to ill-posed linear inverse problems