Publications related to On the Trade-off between Flatness and Optimization in Distributed Learning

Related publications (14)

A Box-Spline Framework for Inverse Problems With Continuous-Domain Sparsity Constraints

Michaël Unser, Aleix Boquet I Pujadas, Mehrsa Pourya

The formulation of inverse problems in the continuum eliminates discretization errors and allows for the exact incorporation of priors. In this paper, we formulate a continuous-domain inverse problem over a search space of continuous and piecewise-linear f ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Regularity Matters: Designing Practical FPGA Switch-Blocks

Paolo Ienne, Stefan Nikolic

Several techniques have been proposed for automatically searching for FPGA switch-blocks which typically show some tangible advantage over the well-known academic architectures. However, the resulting switch-blocks usually exhibit high levels of irregulari ...

Assoc Computing Machinery2023

Estimation of discrete choice models with hybrid stochastic adaptive batch size algorithms

Michel Bierlaire, Virginie Janine Camille Lurkin, Timothy Michael Hillel, Gael Lederrey

The emergence of Big Data has enabled new research perspectives in the discrete choice community. While the techniques to estimate Machine Learning models on a massive amount of data are well established, these have not yet been fully explored for the esti ...

2021

Assisted specification of discrete choice models

Michel Bierlaire, Timothy Michael Hillel, Nicola Marco Ortelli

Determining appropriate utility specifications for discrete choice models is time-consuming and prone to errors. With the availability of larger and larger datasets, as the number of possible specifications exponentially grows with the number of variables ...

ELSEVIER SCI LTD2021

A New Lighting on Analytical Discrete Sensitivities in the Context of IsoGeometric Shape Optimization

Thibaut Hirschler

Isogeometric shape optimization has been now studied for over a decade. This contribution aims at compiling the key ingredients within this promising framework, with a particular attention to sensitivity analysis. Based on all the researches related to iso ...

2021

Dynamic lane restrictions on congested arterials

Nikolaos Geroliminis

Buses operating in mixed traffic experience problems with delay and travel time variability in peak periods. Numerous transit priority measures are found in the literature but most rely on separating buses from other vehicles. Complete separation such as d ...

PERGAMON-ELSEVIER SCIENCE LTD2020

A Mixed-Integer Linear Programming Formulation for Optimizing Multi-Scale Material and Energy Integration

François Maréchal, Ivan Daniel Kantor, Hür Ebuzer Bütün, Jean-Loup Sylvain Robineau

This research presents a mathematical formulation for optimizing integration of complex industrial systems from the level of unit operations to processes, entire plants, and finally to considering industrial symbiosis opportunities between plants. The fram ...

2020

Distributed Multi-Building Coordination for Demand Response

Colin Neil Jones, Altug Bitlislioglu

This paper presents a distributed optimization algorithm tailored for solving optimal control problems arising in multi-building coordination. The buildings coordinated by a grid operator, join a demand response program to balance the voltage surge by usin ...

ELSEVIER2020

The Minimization of Public Facilities With Enhanced Genetic Algorithms Using War Elimination

Michael Mark

In this paper, we focus on the problem of minimizing a network of state facilities that provide essential public services (schools, offices, and hospitals). The goal is to reduce the size of the network in order to minimize the costs associated with it. Ho ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2019

Machine learning methods to assist energy system optimization

Jean-Louis Scartezzini, Amarasinghage Tharindu Dasun Perera, Vahid Moussavi Nik

This study evaluates the potential of supervised and transfer learning techniques to assist energy system optimization. A surrogate model is developed with the support of a supervised learning technique (by using artificial neural network) in order to bypa ...

2019

Adversarially Robust Optimization with Gaussian Processes

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturba ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018

Optimization of Traffic Signals for Transit Priority in Arterials with Dedicated Bus Lanes and Stochastic Arrivals: A System-Oriented Approach

Nikolaos Geroliminis, Mohsen Ramezani Ghalenoei

2015

Viability Principles for Constrained Optimization Using a (1+1)-CMA-ES

Dario Floreano, Andrea Maesani

Viability Evolution is an abstraction of artificial evolution which operates by eliminating candidate solutions that do not satisfy viability criteria. Viability criteria are defined as boundaries on the values of objectives and constraints of the problem ...

Springer International Publishing2014

Automatic Generation of Reduced CPG Control Networks for Locomotion of Arbitrary Modular Robot Structures

Auke Ijspeert, Alexander Spröwitz, Massimo Vespignani, Rico Möckel, Soha Pouya, Jesse van den Kieboom, Stéphane Bonardi

The design of efficient locomotion controllers for arbitrary structures of reconfigurable modular robots is challenging because the morphology of the structure can change dynamically during the completion of a task. In this paper, we propose a new method t ...

2014