paper-with-me

Papers

Supervised Stochastic Gradient Algorithms for Multi-Trial Source Separation

2025-08-28 · Ronak Mehta, Mateus Piovezan Otto, Noah Stanis, Azadeh Yazdan-Shahmorad, Zaid Harchaoui arxiv

We develop a stochastic algorithm for independent component analysis that incorporates multi-trial supervision, which is available in many scientific contexts. The method blends a proximal gradient-type algorithm in the space of invertible matrices with joint learning of a prediction model through backpropagation. We illustrate the proposed algorithm on synthetic and real data experiments. In particular, owing to the additional supervision, we observe an increased success rate of the non-convex optimization and the improved interpretability of the independent components.

📄 PDF Abstract BibTeX arXiv:2508.20618

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics

2022-07-25 · Jeffrey Negrea, Jun Yang, Haoyue Feng, Daniel M. Roy 외

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory. We address this theory--practice gap by characterizing …

Statistical Adaptive Stochastic Gradient Methods

2020-02-25 · Pengchuan Zhang, Hunter Lang, Qiang Liu, Lin Xiao

We propose a statistical adaptive procedure called SALSA for automatically scheduling the learning rate (step size) in stochastic gradient methods. SALSA first uses a smoothed stochastic line-search procedure to graduall…

Scheduling

Stochastic Gradients under Nuisances

2025-08-28 · Facheng Yu, Ronak Mehta, Alex Luedtke, Zaid Harchaoui arxiv

Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learnin…

Self-Supervised LearningCausal Inference

Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)

2013-06-10 · NeurIPS 2013 12 · Francis Bach, Eric Moulines

We consider the stochastic approximation problem where a convex function has to be minimized, given only the knowledge of unbiased estimates of its gradients at certain points, a framework which includes machine learning…

BIG-bench Machine Learningregression

Fast Distributed Stochastic Scheduling for A Multi-Energy Industrial Park

2021-10-27 · Dafeng Zhu, Bo Yang, Zhaojian Wang, Chengbin Ma 외

The multi-energy management framework of industrial parks advocates energy conversion and scheduling, which takes full advantage of the compensation and temporal availability of multiple energy. However, how to exploit e…

energy managementManagementSchedulingStochastic Optimization