arXiv Machine Learning June 24, 2026 By Emanuele Zangrando, Sara Venturini, Francesco Rinaldi, Francesco Tudisco

Constrained Variable Projection for Structured Problems

Read the original on arXiv Machine Learning →

arXiv:2606. 23939v1 Announce Type: cross Abstract: Variable projection is a classical technique for separable nonlinear least-squares problems, in which variables that enter linearly are eliminated exactly, yielding a reduced nonlinear problem.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 15

Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization

arXiv:2609.15679v1 Announce Type: cross Abstract: This paper studies projection-free algorithms for stochastic constrained multi-level compositional optimization. In this context, the objective funct...

By Wei Jiang, Sifan Yang, Wenhao Yang, Yibo Wang, Yuanyu Wan, Zechao Li, Lijun Zhang

arXiv Machine Learning

Jul 2

Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates

arXiv:2503. 24075v4 Announce Type: replace-cross Abstract: Low-rank optimization problems with sparse simplex constraints involve variables that must satisfy nonnegativity, sparsity, and sum-to-1 conditions, making their optimization particularly challenging due to the interplay between low-rank structures and constraints.

By Flavia Esposito, Andersen Ang

efficiency

arXiv Machine Learning

4d ago

Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning

arXiv:2609.36310v1 Announce Type: new Abstract: Everywhere learning provides a principled framework for training AI models under constraints that must hold throughout the data distribution. In the du...

By Ignacio Boero, Jonathan Nixon, Alejandro Ribeiro

arXiv Machine Learning

Jun 16

Self-Supervised Learning of Iterative Solvers for Constrained Optimization

arXiv:2409. 08066v3 Announce Type: replace Abstract: The real-time solution of parametric optimization problems is critical for applications that demand high accuracy under tight real-time constraints, such as model predictive control.

By Lukas L\"uken, Sergio Lucia

benchmarks

arXiv Machine Learning

Jun 15

Neural Slack Variables for Shape Constraints

arXiv:2606. 13803v1 Announce Type: new Abstract: Enforcing functional inequality constraints such as monotonicity and convexity in neural networks is a fundamental challenge in many industrial and scientific applications.

By Ruben Wiedemann, Antoine Jacquier, Lukas Gonon

arXiv Machine Learning

Jun 16

A Fully First-Order Layer for Differentiable Optimization

arXiv:2512. 02494v2 Announce Type: replace Abstract: Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems.

By Zihao Zhao, Kai-Chia Mo, Shing-Hei Ho, Brandon Amos, Kai Wang

One email a morning, machine-written

Related stories

Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization

Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates

Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning

Self-Supervised Learning of Iterative Solvers for Constrained Optimization

Neural Slack Variables for Shape Constraints

A Fully First-Order Layer for Differentiable Optimization