paper-with-me

Papers

Convex Relaxation for Solving Large-Margin Classifiers in Hyperbolic Space

2024-05-27 · Sheng Yang, Peihan Liu, Cengiz Pehlevan

Hyperbolic spaces have increasingly been recognized for their outstanding performance in handling data with inherent hierarchical structures compared to their Euclidean counterparts. However, learning in hyperbolic spaces poses significant challenges. In particular, extending support vector machines to hyperbolic spaces is in general a constrained non-convex optimization problem. Previous and popular attempts to solve hyperbolic SVMs, primarily using projected gradient descent, are generally sensitive to hyperparameters and initializations, often leading to suboptimal solutions. In this work, by first rewriting the problem into a polynomial optimization, we apply semidefinite relaxation and sparse moment-sum-of-squares relaxation to effectively approximate the optima. From extensive empirical experiments, these methods are shown to perform better than the projected gradient descent approach.

📄 PDF Abstract BibTeX arXiv:2405.17198

Code (1)

yangshengaa/hsvm-relax 공식 구현

Similar Papers 제목 키워드 기반

Constrained fractional set programs and their application in local clustering and community detection

2013-06-14 · Thomas Bühler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein

The (constrained) minimization of a ratio of set functions is a problem frequently occurring in clustering and community detection. As these optimization problems are typically NP-hard, one uses convex or spectral relaxa…

ClusteringCommunity Detection

Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers

2020-02-22 · Chen Zhu, Renkun Ni, Ping-Yeh Chiang, Hengduo Li 외

Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical robustness. In principle, convex relaxat…

New Convex Relaxations for MRF Inference With Unknown Graphs

2019-10-01 · ICCV 2019 10 · Zhenhua Wang, Tong Liu, Qinfeng Shi, M. Pawan Kumar 외

Treating graph structures of Markov random fields as unknown and estimating them jointly with labels have been shown to be useful for modeling human activity recognition and other related tasks. We propose two novel rela…

Activity RecognitionHuman Activity Recognition

On the Convergence of Stochastic Gradient Descent with Low-Rank Projections for Convex Low-Rank Matrix Problems

2020-01-31 · Dan Garber

We revisit the use of Stochastic Gradient Descent (SGD) for solving convex optimization problems that serve as highly popular convex relaxations for many important low-rank matrix recovery problems such as \textit{matrix…

Matrix CompletionRetrieval

CRVI: Convex Relaxation for Variational Inference

2018-07-01 · ICML 2018 7 · Ghazal Fazelnia, John Paisley

We present a new technique for solving non-convex variational inference optimization problems. Variational inference is a widely used method for posterior approximation in which the inference problem is transformed …

Inference OptimizationregressionVariational Inference