NSM Converges to a k-NN Regressor Under Loose Lipschitz Estimates

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.

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

Effective fall-detection and classification systems are vital in mitigating severe medical and economical consequences of falls to people in the fall risk groups. One class of such systems is based on wearable sensors. While there is a vast amount of acade ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

In high dimension, low sample size (HDLSS) settings, classifiers based on Euclidean distances like the nearest neighbor classifier and the average distance classifier perform quite poorly if differences between locations of the underlying populations get m ...

Deep learning algorithms are responsible for a technological revolution in a variety oftasks including image recognition or Go playing. Yet, why they work is not understood.Ultimately, they manage to classify data lying in high dimension – a feat generical ...

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

The use of drones in search and rescue (SAR) missions can be very cognitively demanding. Since high levels of cognitive workload can negatively affect human performance, there is a risk of compromising the mission and leading to failure with catastrophic o ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Cities are facing unprecedented challenges to their environments and residents due to continuous growth, including urban overheating, daylight accessibility, noise, and air pollution. This requires a holistic approach to the research and implementation of ...

In solid mechanics, linear structures often exhibit (local) nonlinear behavior when close to failure. For instance, the elastic deformation of a structure becomes plastic after being deformed beyond recovery. To properly assess such problems in a real-life ...

The amount of data that we produce and consume is larger than it has been at any point in the history of mankind, and it keeps growing exponentially. All this information, gathered in overwhelming volumes, often comes with two problematic characteristics: ...

A sliding-window k-NN query (k-NN/w query) continuously monitors incoming data stream objects within a sliding window to identify k closest objects to a query. It enables effective filtering of data objects streaming in at high rates from potentially distr ...

This paper addresses the problem of 3D face recognition using simultaneous sparse approximations on the sphere. The 3D face point clouds are first aligned with a novel and fully automated registration process. They are then represented as signals on the 2D ...

This paper addresses the problem of representing multimedia information under a compressed form that permits efficient classification. The semantic coding problem starts from a subspace method where dimensionality reduction is formulated as a matrix factor ...

In this paper, we focus on the use of random projections as a dimensionality reduction tool for sampled manifolds in high-dimensional Euclidean spaces. We show that geodesic paths approximations from nearest neighbors Euclidean distances are well-preserved ...

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

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 ...

NSM Converges to a k-NN Regressor Under Loose Lipschitz Estimates

Chat with Graph Search

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Classification of fall directions via wearable motion sensors

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

On Generalizations of Some Distance Based Classifiers for HDLSS Data

Landscape and training regimes in deep learning

A comparative analysis of gene expression profiling by statistical and machine learning approaches

Cognitive workload monitoring in virtual reality based rescue missions with drones

Learning to Reason with Neural Networks: Principles and Methods

A multidomain approach to neighbourhood typology for urban environmental studies

Model order reduction for large-scale structures with local nonlinearities

Graph-based Methods for Visualization and Clustering

Distributed processing of continuous sliding-window k-NN queries for data stream filtering

3D Face Recognition with Sparse Spherical Representations

Semantic coding by supervised dimensionality reduction

On the estimation of geodesic paths on sampled manifolds under random projections

Asymptotics of feature learning in two-layer networks after one gradient-step

On the Generalization of Stochastic Gradient Descent with Momentum