Publications related to Party-list proportional representation

Model agnostic methods meta-learn despite misspecifications

Nicolas Henri Bernard Flammarion, Oguz Kaan Yüksel, Etienne Patrice Boursier

Due to its empirical success on few shot classification and reinforcement learning, meta-learning recently received a lot of interest. Meta-learning leverages data from previous tasks to quickly learn a new task, despite limited data. In particular, model ...

2023

Dynamic environmental flows using hydrodynamic-based solutions for sustainable hydropower

Giovanni De Cesare, Paolo Perona

Water diversions from rivers and torrents for anthropic uses of the resource alter the natural flow regime. As a measure, environmental flows have been prescribed and often are enforced by law to follow policies (e.g., minimal flow, proportional redistribu ...

CRC Press/Balkema2023

MulT: An End-to-End Multitask Learning Transformer

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Deblina Bhattacharjee

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estimation, 2D keypoint detection, and edg ...

2022

Linear and nonlinear excitation of TAE modes by external electromagnetic perturbations using ORB5

Laurent Villard, Emmanuel Lanti, Alberto Bottino, Mohsen Sadr

The excitation of toroidicity-induced Alfven eigenmodes (TAEs) using prescribed external electromagnetic perturbations (hereafter 'antenna') acting on a confined toroidal plasma, as well as its nonlinear couplings to other modes in the system, is studied. ...

IOP Publishing Ltd2022

Frequency dependence in GW made simple using a multipole approximation

Tommaso Chiarotti, Andrea Ferretti

In the GW approximation, the screened interaction W is a nonlocal and dynamical potential that usually has a complex frequency dependence. A full description of such a dependence is possible but often computationally demanding. For this reason, it is still ...

AMER PHYSICAL SOC2021

A Shared Representation for Photorealistic Driving Simulators

Alexandre Massoud Alahi, Saeed Saadatnejad, Taylor Ferdinand Mordan, Siyuan Li

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs), providing high-fidel ...

2021

Frontiers of (Pareto) Optimal and Sustainable Water Management for Hydropower and Ecology

David Andrew Barry, Paolo Perona, Amin Niayifar, Pierre Razurel

River regulation alters the natural flow regime of streams with consequent impacts on terrestrial and aquatic habitats of the riparian zone. The severity of such impacts can be modulated by changing the redistribution rules at water intakes and reservoirs. ...

2021

Recursive evaluation and iterative contraction of N-body equivariant features

Michele Ceriotti, Sergey Pozdnyakov, Jigyasa Nigam

Mapping an atomistic configuration to a symmetrized N-point correlation of a field associated with the atomic positions (e.g., an atomic density) has emerged as an elegant and effective solution to represent structures as the input of machine-learning algo ...

2020

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.

Party-list proportional representation

Technosignatures Longevity and Lindy's Law

Model agnostic methods meta-learn despite misspecifications

Dynamic environmental flows using hydrodynamic-based solutions for sustainable hydropower

MulT: An End-to-End Multitask Learning Transformer

Linear and nonlinear excitation of TAE modes by external electromagnetic perturbations using ORB5

Frequency dependence in GW made simple using a multipole approximation

A Shared Representation for Photorealistic Driving Simulators

Frontiers of (Pareto) Optimal and Sustainable Water Management for Hydropower and Ecology

Recursive evaluation and iterative contraction of N-body equivariant features

Learning Graphs From Data: A Signal Representation Perspective

Graph Chatbot

Chat with Graph Search

Technosignatures Longevity and Lindy's Law

Linear and nonlinear excitation of TAE modes by external electromagnetic perturbations using ORB5

Frontiers of (Pareto) Optimal and Sustainable Water Management for Hydropower and Ecology

Dynamic environmental flows using hydrodynamic-based solutions for sustainable hydropower

Model agnostic methods meta-learn despite misspecifications

Learning Graphs From Data: A Signal Representation Perspective

Frequency dependence in GW made simple using a multipole approximation

Recursive evaluation and iterative contraction of N-body equivariant features

MulT: An End-to-End Multitask Learning Transformer

A Shared Representation for Photorealistic Driving Simulators