Publications related to End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Related publications (37)

A Stochastic Approach to Contact-rich Manipulation

For robots to operate in unstructured environments, they are required to interact with objects through contact. Those contacts may be used to push objects to the side, deform objects, or manipulate objects in-hand. This thesis addresses the problem of cont ...

EPFL2025

Dimensionless Group-Driven Ensemble Neural Networks for Robust Design Optimisation in Engineering

Jürg Alexander Schiffmann, Soheyl Massoudi

This work aims to develop a scalable surrogate modelling framework for robust multidisciplinary design optimisation (RMDO) in complex engineering systems. Focusing on gas-bearing supported rotors, it addresses the need to maintain system performance under ...

Oxford University Press (OUP)2025

First and Zeroth-Order Implementations of the Regularized Newton Method with Lazy Approximated Hessians

Nikita Doikov

In this work, we develop first-order (Hessian-free) and zeroth-order (derivative-free) implementations of the Cubically Regularized Newton Method for solving general non-convex optimization problems. For that, we employ finite difference approximations of ...

SPRINGER/PLENUM PUBLISHERS2025

Convex Computation of Value-at-risk Bounds for Stochastic Processes

Matteo Raphael Tacchi

This article formulates algorithms to upper-bound the maximum value-at-risk (VaR) of a state function along trajectories of stochastic processes. The VaR is upper bounded by two methods: minimax tail-bounds (Cantelli/Vysochanskij-Petunin) and Expected Shor ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2025

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

Anne-Clémence Corminboeuf, Friedrich Eisenbrand, Rubén Laplaza Solanas, Puck Elisabeth van Gerwen, Ksenia Briling, Jan Weinreich, Matthieu Nicolas Haeberle

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 ...

IOP Publishing Ltd2025

A shortcut model for batch distillation columns using pertinent effective factors

Dominique Bonvin

A shortcut model is a low-order model that provides a simplified representation of a complex process, thereby enabling faster and more efficient analysis, design and optimization without the computational intensity of a full-scale model. For continuous dis ...

Elsevier2025

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models

Philippe Schwaller, Jeff Guo

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors ...

ROYAL SOC CHEMISTRY2025

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Safe Deep Neural Networks

Kyle Michael Matoba

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 ...

EPFL2024

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

Mattia Atzeni

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 ...

EPFL2024

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

Jean-Paul Richard Kneib, Emma Elizabeth Tolley, Michele Bianco, Tianyue Chen

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 ...

Oxford Univ Press2024

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Romain Christophe Rémy Fleury, Janez Rus

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 ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Incorporating Projective Geometry into Deep Learning

Michal Jan Tyszkiewicz

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

EPFL2024

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Alexander Carl Unnervik

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

EPFL2024

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Arnout Jan J Devos

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

EPFL2024

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Edoardo Charbon, Claudio Bruschini, Andrei Ardelean, Paul Mos, Yang Lin

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

Nature Portfolio2024

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

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 ...

EPFL2024

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Zenodo2024

Machine Learning for Modeling Stock Returns

Teng Andrea Xu

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, ...

EPFL2024