paper-with-me

Papers

Conic Descent Redux for Memory-Efficient Optimization

2023-08-13 · Bingcong Li, Georgios B. Giannakis

Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks. This contribution revisits a recently developed first-order conic descent (CD) solver, and advances it in three aspects: intuition, theory, and algorithmic implementation. It is found that CD can afford an intuitive geometric derivation that originates from the dual problem. This opens the door to novel algorithmic designs, with a momentum variant of CD, momentum conic descent (MOCO) exemplified. Diving deeper into the dual behavior CD and MOCO reveals: i) an analytically justified stopping criterion; and, ii) the potential to design preconditioners to speed up dual convergence. Lastly, to scale semidefinite programming (SDP) especially for low-rank solutions, a memory efficient MOCO variant is developed and numerically validated.

📄 PDF Abstract BibTeX arXiv:2308.07343

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

InfoNCE 설명 없음
Batch Normalization 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
MoCo 설명 없음

Similar Papers 제목 키워드 기반

Data Dieting in GAN Training

2020-04-07 · Jamal Toutouh, Una-May O'Reilly, Erik Hemberg

We investigate training Generative Adversarial Networks, GANs, with less data. Subsets of the training dataset can express empirical sample diversity while reducing training resource requirements, e.g. time and memory. W…

Diversity

Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices

2020-12-01 · NeurIPS 2020 12 · John C. Duchi, Oliver Hinder, Andrew Naber, Yinyu Ye

We present an extension of the conditional gradient method to problems whose feasible sets are convex cones. We provide a convergence analysis for the method and for variants with nonconvex objectives, and we extend the …

Matrix CompletionRetrieval

Dual Lagrangian Learning for Conic Optimization

2024-02-05 · Mathieu Tanneau, Pascal Van Hentenryck

This paper presents Dual Lagrangian Learning (DLL), a principled learning methodology for dual conic optimization proxies. DLL leverages conic duality and the representation power of ML models to provide high-duality, du…

Self-Supervised Learningvalid

Laconic Deep Learning Computing

2018-05-10 · Sayeh Sharify, Mostafa Mahmoud, Alberto Delmas Lascorz, Milos Nikolic 외

We motivate a method for transparently identifying ineffectual computations in unmodified Deep Learning models and without affecting accuracy. Specifically, we show that if we decompose multiplications down to the bit le…

2kDeep Learningimage-classificationImage Classification

Stochastic interior-point methods for smooth conic optimization with applications

2024-12-17 · Chuan He, Zhanwang Deng

Conic optimization plays a crucial role in many machine learning (ML) problems. However, practical algorithms for conic constrained ML problems with large datasets are often limited to specific use cases, as stochastic a…