paper-with-me

Papers

Sparse projections onto the simplex

2012-06-07 · Anastasios Kyrillidis, Stephen Becker, Volkan Cevher and, Christoph Koch

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the $\ell_1$-norm. However, several important learning applications cannot benefit from this approach as they feature these convex norms as constraints in addition to the non-convex rank and sparsity constraints. In this setting, we derive efficient sparse projections onto the simplex and its extension, and illustrate how to use them to solve high-dimensional learning problems in quantum tomography, sparse density estimation and portfolio selection with non-convex constraints.

📄 PDF Abstract BibTeX arXiv:1206.1529

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Rankmax: An Adaptive Projection Alternative to the Softmax Function

2020-12-01 · NeurIPS 2020 12 · Weiwei Kong, Walid Krichene, Nicolas Mayoraz, Steffen Rendle 외

Several machine learning models involve mapping a score vector to a probability vector. Usually, this is done by projecting the score vector onto a probability simplex, and such projections are often characterized as Lip…

Blended Conditional Gradients: the unconditioning of conditional gradients

2018-05-18 · Gábor Braun, Sebastian Pokutta, Dan Tu, Stephen Wright

We present a blended conditional gradient approach for minimizing a smooth convex function over a polytope P, combining the Frank--Wolfe algorithm (also called conditional gradient) with gradient-based steps, different f…

Projection onto the capped simplex

2015-03-03 · Weiran Wang, Canyi Lu

We provide a simple and efficient algorithm for computing the Euclidean projection of a point onto the capped simplex---a simplex with an additional uniform bound on each coordinate---together with an elementary proof. B…

Differentiable Zero-One Loss via Hypersimplex Projections

2026-02-26 · Camilo Gomez, Pengyang Wang, Liansheng Tang arxiv

Recent advances in machine learning have emphasized the integration of structured optimization components into end-to-end differentiable models, enabling richer inductive biases and tighter alignment with task-specific o…

Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning

2025-01-04 · Zhongyi Zhou, Yaxin Peng, Pin Yi, Minjie Zhu 외

Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability …

Continual LearningMixture-of-Experts