Traveling Salesman in Reverse: Conditional Markov Entropy for Trajectory Segmentation

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.

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

We introduce a model-independent method for the efficient simulation of low-entropy systems, whose dynamics can be accurately described with a limited number of states. Our method leverages the time-dependent variational principle to efficiently integrate ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

Barocaloric (BC) materials provide cheaper and more energy efficient alternatives to traditional refrigerants. Some liquid alkanes were recently shown to exhibit a colossal BC effect, matching the entropy changes in commercial vapour-liquid refrigerants. D ...

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Hand gestures are one of the most natural and expressive way for humans to convey information, and thus hand gesture recognition has become a research hotspot in the human-machine interface (HMI) field. In particular, biological signals such as surface ele ...

Given two jointly distributed random variables (X,Y), a functional representation of X is a random variable Z independent of Y, and a deterministic function g(⋅,⋅) such that X=g(Y,Z). The problem of finding a minimum entropy functional representation is kn ...

Quantum random number generators (QRNGs) are a burgeoning technology used for a variety of applications, including modern security and encryption systems. Typical methods exploit an entropy source combined with an extraction or bit generation circuit in or ...

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with a single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both Bayes-optimal (BO) ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

The minimization of a data-fidelity term and an additive regularization functional gives rise to a powerful framework for supervised learning. In this paper, we present a unifying regularization functional that depends on an operator L\documentclass[12pt]{ ...

In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...

Traveling Salesman in Reverse: Conditional Markov Entropy for Trajectory Segmentation

Chat with Graph Search

Robust NAS under adversarial training: benchmark, theory, and beyond

Sparse autoregressive neural networks for classical spin systems

Aggregating Spatial and Photometric Context for Photometric Stereo

Adaptive variational low-rank dynamics for open quantum systems

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Efficient local linearity regularization to overcome catastrophic overfitting

Pressure-freezing of dodecane: exploring the crystal structures, formation kinetics and phase diagrams for colossal barocaloric effects in n-alkanes

Neural Distributed Image Compression with Cross-Attention Feature Alignment

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Motor-Unit Ordering of Blindly-Separated Surface-EMG Signals for Gesture Recognition

Information Spectrum Converse for Minimum Entropy Couplings and Functional Representations

A 3.3-Gb/s SPAD-Based Quantum Random Number Generator

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

Learning curves for the multi-class teacher-student perceptron

Deep Learning Generalization with Limited and Noisy Labels

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

From Kernel Methods to Neural Networks: A Unifying Variational Formulation

Deep Learning for 3D Surface Modelling and Reconstruction