paper-with-me

홈 › Papers

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees

2025-06-10 · William de Vazelhes, Xiao-Tong Yuan, Bin Gu

In sparse optimization, enforcing hard constraints using the $\ell_0$ pseudo-norm offers advantages like controlled sparsity compared to convex relaxations. However, many real-world applications demand not only sparsity constraints but also some extra constraints. While prior algorithms have been developed to address this complex scenario with mixed combinatorial and convex constraints, they typically require the closed form projection onto the mixed constraints which might not exist, and/or only provide local guarantees of convergence which is different from the global guarantees commonly sought in sparse optimization. To fill this gap, in this paper, we study the problem of sparse optimization with extra support-preserving constraints commonly encountered in the literature. We present a new variant of iterative hard-thresholding algorithm equipped with a two-step consecutive projection operator customized for these mixed constraints, serving as a simple alternative to the Euclidean projection onto the mixed constraint. By introducing a novel trade-off between sparsity relaxation and sub-optimality, we provide global guarantees in objective value for the output of our algorithm, in the deterministic, stochastic, and zeroth-order settings, under the conventional restricted strong-convexity/smoothness assumptions. As a fundamental contribution in proof techniques, we develop a novel extension of the classic three-point lemma to the considered two-step non-convex projection operator, which allows us to analyze the convergence in objective value in an elegant way that has not been possible with existing techniques. In the zeroth-order case, such technique also improves upon the state-of-the-art result from de Vazelhes et. al. (2022), even in the case without additional constraints, by allowing us to remove a non-vanishing system error present in their work.

📄 PDF Abstract BibTeX arXiv:2506.08558

Code (1)

wdevazelhes/2sp_icml2025 공식 구현

Tasks

LEMMA

Similar Papers 제목 키워드 기반

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

2017-04-07 · ICCV 2017 10 · Ryo Yonetani, Vishnu Naresh Boddeti, Kris M. Kitani, Yoichi Sato

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and …

Privacy Preserving

PockEngine: Sparse and Efficient Fine-tuning in a Pocket

2023-10-26 · Ligeng Zhu, Lanxiang Hu, Ji Lin, Wei-Chen Wang 외

On-device learning and efficient fine-tuning enable continuous and privacy-preserving customization (e.g., locally fine-tuning large language models on personalized data). However, existing training frameworks are design…

CPUGPUPrivacy Preserving

Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections

2019-09-02 · Diego Valsesia, Sophie Marie Fosson, Chiara Ravazzi, Tiziano Bianchi 외

Embeddings provide compact representations of signals in order to perform efficient inference in a wide variety of tasks. In particular, random projections are common tools to construct Euclidean distance-preserving embe…

MorphoFlow: Sparse-Supervised Generative Shape Modeling with Adaptive Latent Relevance

2026-04-13 · Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen Elhabian arxiv

Statistical shape modeling (SSM) is central to population level analysis of anatomical variability, yet most existing approaches rely on densely annotated segmentations and fixed latent representations. These requirement…

Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate

2026-05-24 · Huangyu Xu, Jingqin Yang, Qianqian Xu, Jiaye Teng arxiv

Sparse optimization is a fundamental challenge in various practical applications. A popular approach to sparse optimization is $\ell_p$ regularization. However, it may encounter optimization instability due to the unboun…