paper-with-me

Papers

LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

2024-09-04 · Xiaoyuan Zhang, Liang Zhao, Yingying Yu, Xi Lin, Yifan Chen, Han Zhao, Qingfu Zhang

Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc. Instead of reducing multiple objective functions into a scalar objective, MOPs aim to optimize for the so-called Pareto optimality or Pareto set learning, which involves optimizing more than one objective function simultaneously, over models with thousands / millions of parameters. Existing benchmark libraries for MOPs mainly focus on evolutionary algorithms, most of which are zeroth-order / meta-heuristic methods that do not effectively utilize higher-order information from objectives and cannot scale to large-scale models with thousands / millions of parameters. In light of the above gap, this paper introduces LibMOON, the first multiobjective optimization library that supports state-of-the-art gradient-based methods, provides a fair benchmark, and is open-sourced for the community.

📄 PDF Abstract BibTeX arXiv:2409.02969

Code (1)

xzhang2523/libmoon 공식 구현 pytorch

Tasks

Evolutionary AlgorithmsFairnessMultiobjective OptimizationMulti-Task Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Library 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

PyTorch Tabular: A Framework for Deep Learning with Tabular Data

2021-04-28 · Manu Joseph

In spite of showing unreasonable effectiveness in modalities like Text and Image, Deep Learning has always lagged Gradient Boosting in tabular data - both in popularity and performance. But recently there have been newer…

Deep Learning

ASDL: A Unified Interface for Gradient Preconditioning in PyTorch

2023-05-08 · Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li 외

Gradient preconditioning is a key technique to integrate the second-order information into gradients for improving and extending gradient-based learning algorithms. In deep learning, stochasticity, nonconvexity, and high…

torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models

2020-04-21 · Chiheon Kim, Heungsub Lee, Myungryong Jeong, Woonhyuk Baek 외

We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019). In particular, we develop a set of design components to…

UncertaintyPlayground: A Fast and Simplified Python Library for Uncertainty Estimation

2023-10-23 · Ilia Azizi

This paper introduces UncertaintyPlayground, a Python library built on PyTorch and GPyTorch for uncertainty estimation in supervised learning tasks. The library offers fast training for Gaussian and multi-modal outcome d…

CPUGPUPrediction Intervals

TorchOpt: An Efficient Library for Differentiable Optimization

2022-11-13 · Jie Ren, Xidong Feng, Bo Liu, Xuehai Pan 외

Recent years have witnessed the booming of various differentiable optimization algorithms. These algorithms exhibit different execution patterns, and their execution needs massive computational resources that go beyond a…

CPUGPU