Publications related to Learning from survey propagation: a neural network for MAX-E-3-SAT

Related publications (48)

Learning to Reason with Neural Networks: Principles and Methods

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 ...

EPFL2025

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

Ismail Nejjar

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 ...

EPFL2025

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Thomas Grégoire Stegmüller

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 ...

EPFL2025

Approximation Algorithms for Allocation and Network Design

Etienne Michel François Bamas

In this thesis, we give new approximation algorithms for some NP-hard problems arising in resource allocation and network design. As a resource allocation problem, we study the Santa Claus problem (also known as the MaxMin Fair Allocation problem) in which ...

EPFL2023

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

Anaïs Betsabeh Haget, Maria Boulougouri

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 ...

OXFORD UNIV PRESS2025

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

Boi Faltings, Zeki Doruk Erden

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Springer Science and Business Media Deutschland GmbH2025

Improving Standard-Cell Design Flow using Factored Form Optimization

Giovanni De Micheli, Alessandro Tempia Calvino

Factored form is a powerful multi-level representation of a Boolean function that readily translates into an implementation of the function in CMOS technology. In particular, the number of literals in a factored form correlates strongly with the number of ...

IEEE2023

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

David Atienza Alonso, Giovanni Ansaloni, Marina Zapater Sancho, Irem Boybat Kara, Flavio Ponzina, Joshua Alexander Harrison Klein, Yuxuan Wang, Abu Sebastian

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

Institute of Electrical and Electronics Engineers (IEEE)2025

NP Satisfiability for Arrays as Powers

Viktor Kuncak, Rodrigo Raya

We show that the satisfiability problem for the quantifier-free theory of product structures with the equicardinality relation is inNP. As an application, we extend the combinatory array logic fragmentto handle cardinality constraints. The resulting fragme ...

Springer, Cham2022

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

Fernando Porté Agel, Jiannong Fang, Wenlong Liao

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

2025

On Semi-Algebraic Proofs and Algorithms

Mika Tapani Göös

We give a new characterization of the Sherali-Adams proof system, showing that there is a degree-d Sherali-Adams refutation of an unsatisfiable CNF formula C if and only if there is an ε > 0 and a degree-d conical junta J such that viol_C(x) - ε = J, where ...

Schloss Dagstuhl - Leibniz-Zentrum für Informatik2022

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

Minh Hieu Lê

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 ...

Springer Science and Business Media Deutschland GmbH2025

A Majority Lemma for Randomised Query Complexity

Mika Tapani Göös, Gilbert Théodore Maystre

We show that computing the majority of n copies of a boolean function g has randomised query complexity R(Maj∘gⁿ) = Θ(n⋅R ̅_{1/n}(g)). In fact, we show that to obtain a similar result for any composed function f∘gⁿ, it suffices to prove a sufficiently stro ...

Schloss Dagstuhl - Leibniz-Zentrum für Informatik2021

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

Anne-Marie Kermarrec, Rafael Pereira Pires, Marinus Abraham de Vos, Akash Balasaheb Dhasade, Tuan Anh Nguyen

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

ACM2025

Three-Input Gates for Logic Synthesis

Giovanni De Micheli, Mathias Soeken, Heinz Riener, Eleonora Testa, Dewmini Sudara Marakkalage

Most logic synthesis algorithms work on graph representations of logic functions with nodes associated with arbitrary logic expressions or simple logic functions and iteratively optimize such graphs. While recent multilevel logic synthesis efforts focused ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Cost-Efficiency Trade-offs for Neural Cascade Rankers in Web Search

Ekaterina Trimbach

Web search engines process billions of queries daily, making the balance between computational efficiency and ranking quality crucial. While neural ranking models have shown impressive performance, their computational costs, particularly in feature extract ...

ACM2025

Logic Resynthesis of Majority-Based Circuits by Top-Down Decomposition

Giovanni De Micheli, Heinz Riener, Siang-Yun Lee

Logic resynthesis is the problem of finding a dependency function to re-express a given Boolean function in terms of a given set of divisor functions. In this paper, we study logic resynthesis of majority-based circuits, which is motivated by the increasin ...

IEEE2021

From Boolean functions to quantum circuits: A scalable quantum compilation flow in C++

Giovanni De Micheli, Heinz Riener, Bruno Schmitt Antunes, Giulia Meuli, Fereshte Mozafari Ghoraba

We propose a flow for automated quantum compila- tion. Our flow takes a Boolean function implemented in Python as input and translates it into a format appropriate for reversible logic synthesis. We focus on two quantum compilation tasks: uniform state pre ...

2021

Person Re-Identification and its Application to Multi-Object Tracking

Vladimir Dominic K. Somers

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

EPFL2025

Boolean satisfiability in quantum compilation

Giovanni De Micheli, Mathias Soeken, Heinz Riener, Bruno Schmitt Antunes, Giulia Meuli, Fereshte Mozafari Ghoraba

Quantum compilation is the task of translating a quantum algorithm implemented in a high-level quantum programming language into a technology-dependent instructions flow for a physical quantum computer. To tackle the large gap between the quantum program a ...

ROYAL SOC2020