Publications associées à RAFT: Regularized Adversarial Fine-Tuning to Enhance Deep Reinforcement Learning for Self-Parking

Publications associées (25)

How data structures affect generalization in Kernel Methods and Deep Learning

Artificial Intelligence has revolutionized numerous fields, driving advancements in healthcare, finance, and autonomous systems. At the core of this revolution lies Deep Learning---algorithms that learn representations from data through computational layer ...

EPFL2025

Joint Compression of Multi-model Systems for Edge Devices

Mathieu Salzmann, João Luís Prado Vieira

Deploying deep learning models for computer vision (CV) often requires a careful trade-off between performance, efficiency, and cost. In the context of edge inference of machine learning systems, this trade-off translates into a challenge, as computing and ...

Springer Science and Business Media Deutschland GmbH2025

Adaptive energy reference for machine-learning models of the electronic density of states

Michele Ceriotti, Federico Grasselli, Kevin Kazuki Huguenin-Dumittan, Sanggyu Chong, Wei Bin How

The electronic density of states (DOS) provides information regarding the distribution of electronic energy levels in a material, and can be used to approximate its optical and electronic properties and therefore guide computational materials design. Given ...

2025

Co-optimising Design and Operation of Energy Systems using Reinforcement Learning

Marine Dominique Cauz

The energy transition is ongoing, in Switzerland and abroad, leading to an ever-increasing development of renewable energy sources. These sources are decentralised, heterogeneous, come with a high dependance on weather conditions, and are therefore hard t ...

EPFL2024

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

Zhuan Shi, Gang Wang

Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system ...

IJCAI2024

Low-Resource Speech Recognition and Understanding for Challenging Applications

Juan Pablo Zuluaga Gomez

Automatic speech recognition (ASR) and spoken language understanding (SLU) is the core component of current voice-powered AI assistants such as Siri and Alexa. It involves speech transcription with ASR and its comprehension with natural language understand ...

EPFL2024

Multi-agent Learning with Privacy Guarantees

Elsa Rizk

A multi-agent system consists of a collection of decision-making or learning agents subjected to streaming observations from some real-world phenomenon. The goal of the system is to solve some global learning or optimization problem in a distributed or dec ...

EPFL2023

Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice

Martin Josifoski

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of related tasks available is often small, most of the existing approaches assume ...

2023

Critical analysis of decision variables for high-throughput experimentation (HTE) with perovskite solar cells

Mohammad Khaja Nazeeruddin, François Maréchal, Naveen Bhati

Perovskite solar cells are among the most dominant emerging PV technologies which have shown unparallel improvement in power conversion efficiency in just over a decade. Long charge carrier diffusion lengths and lifetimes, high absorption coefficients, ban ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Graph Representation Learning with Optimal Transport: Analysis and Applications

Effrosyni Simou

In several machine learning settings, the data of interest are well described by graphs. Examples include data pertaining to transportation networks or social networks. Further, biological data, such as proteins or molecules, lend themselves well to graph- ...

EPFL2022

Automatic pathological speech assessment

Parvaneh Janbakhshi

Many pathologies cause impairments in the speech production mechanism resulting in reduced speech intelligibility and communicative ability. To assist the clinical diagnosis, treatment and management of speech disorders, automatic pathological speech asses ...

EPFL2022

Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

Emmanuel Abbé

YY We consider the symmetric binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory communities, with recent connections made to the performan ...

IEEE COMPUTER SOC2022

Autonomous Detection and Deterrence of Pigeons on Buildings by Drones

Dario Floreano, Fabrizio Schiano, Davide Zambrano

Pigeons may transmit diseases to humans and cause damages to buildings, monuments, and other infrastructure. Therefore, several control strategies have been developed, but they have been found to be either ineffective or harmful to animals and often depend ...

2022

Bayesian Inversion for Nonlinear Imaging Models Using Deep Generative Priors

Michaël Unser, Thanh-An Michel Pham, Pakshal Narendra Bohra, Jonathan Yuelin Dong

Most modern imaging systems incorporate a computational pipeline to infer the image of interest from acquired measurements. The Bayesian approach to solve such ill-posed inverse problems involves the characterization of the posterior distribution of the im ...

2022

Collaborative Sampling in Generative Adversarial Networks

Alexandre Massoud Alahi, Yuejiang Liu, Parth Ashit Kothari

The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling. However, this sampling method loses valuable information learned by the discriminator regarding the data distribution. In this work, we propose a co ...

2020

Fast and Robust Distributed Learning in High Dimension

Rachid Guerraoui, El Mahdi El Mhamdi, Sébastien Louis Alexandre Rouault

Could a gradient aggregation rule (GAR) for distributed machine learning be both robust and fast? This paper answers by the affirmative through Multi-Bulyan. Given n workers, f of which are arbitrary malicious (Byzantine) and m = n − f are not, we prove th ...

2020

Efficient Allocations in Constant Time: Towards Scalable Solutions in the Era of Large Scale Intelligent Systems

Boi Faltings, Panayiotis Danassis

The next technological revolution will be interwoven to the proliferation of intelligent systems. As we bridge the gap between physical and cyber worlds, we will give rise to large-scale, multi-agent based technologies. A key challenge that cities of the f ...

IOS PRESS2020

Learning (from) the Electron Density: Transferability, Conformational and Chemical Diversity

Anne-Clémence Corminboeuf, Alberto Fabrizio, Andrea Grisafi, Ksenia Briling

Machine-learning in quantum chemistry is currently booming, with reported applications spanning all molecular properties from simple atomization energies to complex mathematical objects such as the many-body wavefunction. Due to its central role in density ...

2020

Advancing computational and data-driven methods for the design and discovery of nanoporous materials

Seyedmohamad Moosavi

Metal-organic framework (MOFs) and related nanoporous materials have emerged as promising candidates for a variety of applications, such as gas separation and storage, catalysis, sensing, etc. Their building block structure allows us to generate a huge num ...

EPFL2020

Learning Positive Functions with Pseudo Mirror Descent

Negar Kiyavash

The nonparametric learning of positive-valued functions appears widely in machine learning, especially in the context of estimating intensity functions of point processes. Yet, existing approaches either require computing expensive projections or semidefin ...

Curran Associates, Inc.2019