English
Related papers

Related papers: Neural Optimization: Understanding Trade-offs with…

200 papers

The goal of multi-objective optimisation is to identify the Pareto front surface which is the set obtained by connecting the best trade-off points. Typically this surface is computed by evaluating the objectives at different points and then…

Machine Learning · Statistics 2024-06-24 Ben Tu , Nikolas Kantas , Robert M. Lee , Behrang Shafei

In multi-objective optimization, learning all the policies that reach Pareto-efficient solutions is an expensive process. The set of optimal policies can grow exponentially with the number of objectives, and recovering all solutions…

Machine Learning · Computer Science 2022-04-12 Mathieu Reymond , Eugenio Bargiacchi , Ann Nowé

Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply training a subset of their parameters. Such a discovery has a…

Machine Learning · Computer Science 2022-11-15 Andrea Bragagnolo , Enzo Tartaglione , Marco Grangetto

Expensive multi-objective optimization problems can be found in many real-world applications, where their objective function evaluations involve expensive computations or physical experiments. It is desirable to obtain an approximate Pareto…

Neural and Evolutionary Computing · Computer Science 2022-10-18 Xi Lin , Zhiyuan Yang , Xiaoyuan Zhang , Qingfu Zhang

Traditionally, researchers in decision making have focused on attempting to reach Pareto Optimality using horizontal approaches, where optimality is calculated taking into account every participant at the same time. Sometimes, this may…

Multiagent Systems · Computer Science 2016-07-05 Victor Sanchez-Anguix , Reyhan Aydogan , Tim Baarslag , Catholijn M. Jonker

Biological and artificial learning agents face numerous choices about how to learn, ranging from hyperparameter selection to aspects of task distributions like curricula. Understanding how to make these meta-learning choices could offer…

Neural and Evolutionary Computing · Computer Science 2024-07-16 Rodrigo Carrasco-Davis , Javier Masís , Andrew M. Saxe

What is motivation and how does it work? Where do goals come from and how do they vary within and between species and individuals? Why do we prefer some things over others? MEDO is a theoretical framework for understanding these questions…

Neurons and Cognition · Quantitative Biology 2019-11-12 Adam Safron

This paper focuses on developing Pareto-optimal estimation and policy learning to identify the most effective treatment that maximizes the total reward from both short-term and long-term effects, which might conflict with each other. For…

Machine Learning · Computer Science 2024-03-13 Yingrong Wang , Anpeng Wu , Haoxuan Li , Weiming Liu , Qiaowei Miao , Ruoxuan Xiong , Fei Wu , Kun Kuang

In modern deep learning, algorithmic choices (such as width, depth, and learning rate) are known to modulate nuanced resource tradeoffs. This work investigates how these complexities necessarily arise for feature learning in the presence of…

Machine Learning · Computer Science 2023-10-31 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Eran Malach , Cyril Zhang

In markets where algorithmic data processing is increasingly prevalent, recommendation algorithms can substantially affect trade and welfare. We consider a setting in which an algorithm recommends a product based on its value to the buyer…

Theoretical Economics · Economics 2025-06-17 Shota Ichihashi , Alex Smolin

In a multi-objective game, each individual's payoff is a \emph{vector-valued} function of everyone's actions. Under such vectorial payoffs, Pareto-efficiency is used to formulate each individual's best-response condition, inducing…

Computer Science and Game Theory · Computer Science 2018-09-14 Anisse Ismaili

The evolution of gene regulatory networks in variable environments poses Multi-objective Optimization Problem (MOP), where the expression levels of genes must be tuned to meet the demands of each environment. When formalized in the context…

Optimization and Control · Mathematics 2018-04-23 Philippe Nghe , Bela M. Mulder , Sander J. Tans

Overparameterization and overfitting are common concerns when designing and training deep neural networks, that are often counteracted by pruning and regularization strategies. However, these strategies remain secondary to most learning…

Machine Learning · Computer Science 2020-09-01 Malena Reiners , Kathrin Klamroth , Michael Stiglmayr

In a multiobjective optimization problem a solution is called Pareto-optimal if no criterion can be improved without deteriorating at least one of the other criteria. Computing the set of all Pareto-optimal solutions is a common task in…

Data Structures and Algorithms · Computer Science 2020-10-22 Heiko Röglin

This paper provides a novel framework for solving multiobjective discrete optimization problems with an arbitrary number of objectives. Our framework formulates these problems as network models, in that enumerating the Pareto frontier…

Optimization and Control · Mathematics 2018-09-06 David Bergman , Merve Bodur , Carlos Cardonha , Andre A. Cire

One of the arduous tasks in supply chain modelling is to build robust models against irregular variations. During the proliferation of time-series analyses and machine learning models, several modifications were proposed such as…

Artificial Intelligence · Computer Science 2020-04-30 Heerok Banerjee , V. Ganapathy , V. M. Shenbagaraman

Multi-Objective Optimization (MOO) techniques have become increasingly popular in recent years due to their potential for solving real-world problems in various fields, such as logistics, finance, environmental management, and engineering.…

Neural and Evolutionary Computing · Computer Science 2024-07-15 Noor A. Rashed , Yossra H. Ali , Tarik A. Rashid , A. Salih

A common goal in evolutionary multi-objective optimization is to find suitable finite-size approximations of the Pareto front of a given multi-objective optimization problem. While many multi-objective evolutionary algorithms have proven to…

Neural and Evolutionary Computing · Computer Science 2024-09-26 Hao Wang , Angel E. Rodriguez-Fernandez , Lourdes Uribe , André Deutz , Oziel Cortés-Piña , Oliver Schütze

Most approaches for designing self-assembled materials focus on the thermodynamic stability of a target structure or crystal polymorph. Yet in practice, the outcome of a self-assembly process is often controlled by kinetic pathways. Here we…

Soft Condensed Matter · Physics 2025-05-08 Sambarta Chatterjee , William M. Jacobs

We investigate Pareto equilibria for bi-objective optimal control problems. Our framework comprises the situation in which an agent acts with a distributed control in a portion of a given domain, and aims to achieve two distinct (possibly…

Optimization and Control · Mathematics 2023-07-12 Pitágoras P. de Carvalho , Enrique Fernández-Cara , Juan Límaco , Denilson Menezes , Yuri Thamsten