A note on efficient computation of privileged directions in modifier adaptation

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.

Contemporary artificial intelligence (AI) models' exponentially growing complexity translates to their expanding skill sets. They can create language or image content mimicking human creativity and understanding, becoming indispensable tools in education, ...

Segmenting brain tumors is a critical task in medical imaging that relies on advanced deep-learning methods. However, effectively handling complex tumor regions requires more comprehensive and advanced strategies to overcome challenges such as computationa ...

Computing has long been central to technological advancements, where each leap in compute power has catalyzed applications once thought impossible, such as smartphones. Recently, the exponential growth in the compute demand of artificial intelligence (AI) ...

Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...

In this concise contribution, it is demonstrated that Recurrent Neural Networks (RNNs) based on Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction (RSF) laws from synthetic data. The dat ...

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

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 ...

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

In this note, we prove that if a subharmonic function Delta u >= 0 has pure second derivatives partial derivative(ii)u that are signed measures, then their negative part (partial derivative(ii)u)- belongs to L-1 (in particular, it is not singular). We then ...

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 ...

This paper presents the experimental validation of a linear recursive state estimation (SE) process for hybrid AC/DC microgrids proposed in the authors' previous work. The SE uses a unified and linear measurement model that relies on the use of synchronize ...

Activity-based models offer the potential of a far deeper understanding of daily mobility behaviour than trip-based models. However, activity-based models used both in research and practice have often relied on applying sequential choice models between sub ...

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 ...

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 ...

In this paper, we present an exact (i. e. non-approximated) and linear measurement model for hybrid AC/DC microgrids for recursive state estimation (SE). More specifically, an exact linear model of a voltage source converter (VSC) is proposed. It relies on ...

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

The goal of this work is to use anisotropic adaptive finite elements for the numerical simulation of aluminium electrolysis. The anisotropic adaptive criteria are based on a posteriori error estimates derived for simplified problems. First, we consider an ...

Selection bias may arise when data have been chosen in a way that subsequent analysis does not account for. Such bias can arise in climate event attribution studies that are performed rapidly after a devastating "trigger event'', whose occurrence correspon ...

A note on efficient computation of privileged directions in modifier adaptation

Chat with Graph Search

Programming Light Propagation for Efficient Artificial Intelligence

LIU-NET: lightweight Inception U-Net for efficient brain tumor segmentation from multimodal 3D MRI images

Optical Processors for AI Computing and Networking

Scaling the Modalities in Multimodal Foundation Models

Data-driven dynamic friction models based on Recurrent Neural Networks

Stochastic adaptive resampling for the estimation of discrete choice models

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

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

Universal and adaptive methods for robust stochastic optimization

Graph generative deep learning models with an application to circuit topologies

IMPROVED REGULARITY OF SECOND DERIVATIVES FOR SUBHARMONIC FUNCTIONS

Understanding generalization and robustness in modern deep learning

Experimental Validation of a Unified and Linear State Estimation Method for Hybrid AC/DC Microgrids

OASIS: Optimisation-based Activity Scheduling with Integrated Simultaneous choice dimensions

On the Generalization of Stochastic Gradient Descent with Momentum

Random matrix methods for high-dimensional machine learning models

Linear Recursive State Estimation of Hybrid and Unbalanced AC/DC Micro-Grids using Synchronized Measurements

The statistical complexity of early-stopped mirror descent

Adaptive Finite Elements with Large Aspect Ratio. Application to Aluminium Electrolysis

Timing and spatial selection bias in rapid extreme event attribution