paper-with-me

Papers

Follow the bisector: a simple method for multi-objective optimization

2020-07-14 · Alexandr Katrutsa, Daniil Merkulov, Nurislam Tursynbek, Ivan Oseledets

This study presents a novel Equiangular Direction Method (EDM) to solve a multi-objective optimization problem. We consider optimization problems, where multiple differentiable losses have to be minimized. The presented method computes descent direction in every iteration to guarantee equal relative decrease of objective functions. This descent direction is based on the normalized gradients of the individual losses. Therefore, it is appropriate to solve multi-objective optimization problems with multi-scale losses. We test the proposed method on the imbalanced classification problem and multi-task learning problem, where standard datasets are used. EDM is compared with other methods to solve these problems.

📄 PDF Abstract BibTeX arXiv:2007.06937

Code (1)

amkatrutsa/edm 공식 구현 pytorch

Tasks

imbalanced classificationMulti-Task Learning

Similar Papers 제목 키워드 기반

Novel Policy Seeking with Constrained Optimization

2020-05-21 · Hao Sun, Zhenghao Peng, Bo Dai, Jian Guo 외

In problem-solving, we humans can come up with multiple novel solutions to the same problem. However, reinforcement learning algorithms can only produce a set of monotonous policies that maximize the cumulative reward bu…

DiversityMuJoCoreinforcement-learningReinforcement Learning+1

Tropical Bisectors and Carlini-Wagner Attacks

2025-03-28 · Gillian Grindstaff, Julia Lindberg, Daniela Schkoda, Miruna-Stefana Sorea 외

Pasque et al. showed that using a tropical symmetric metric as an activation function in the last layer can improve the robustness of convolutional neural networks (CNNs) against state-of-the-art attacks, including the C…

A bisector line field approach to interpolation of orientation fields

2019-07-26 · Nicolas Boizot, Ludovic Sacchelli

We propose an approach to the problem of global reconstruction of an orientation field. The method is based on a geometric model called "bisector line fields", which maps a pair of vector fields to an orientation field, …

Fuzzy Hierarchical Multiplex

2025-12-10 · Alexis Kafantaris arxiv

A new fuzzy optimization framework that extends FCM causality is proposed. This model utilizes the dynamics to map data into metrics and create a framework that examines logical implication and hierarchy of concepts usin…

Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis

2025-09-18 · Sihan Zeng, Benjamin Patrick Evans, Sujay Bhatt, Leo Ardon 외 arxiv

We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large population of homogeneous followers. Th…