paper-with-me

Papers

Orbit Regularization

2014-12-01 · NeurIPS 2014 12 · Renato Negrinho, Andre Martins

We propose a general framework for regularization based on group majorization. In this framework, a group is defined to act on the parameter space and an orbit is fixed; to control complexity, the model parameters are confined to lie in the convex hull of this orbit (the orbitope). Common regularizers are recovered as particular cases, and a connection is revealed between the recent sorted 1 -norm and the hyperoctahedral group. We derive the properties a group must satisfy for being amenable to optimization with conditional and projected gradient algorithms. Finally, we suggest a continuation strategy for orbit exploration, presenting simulation results for the symmetric and hyperoctahedral groups.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the implicit regularization of Langevin dynamics with projected noise

2026-02-12 · Govind Menon, Austin J. Stromme, Adrien Vacher arxiv

We study Langevin dynamics with noise projected onto the directions orthogonal to an isometric group action. This mathematical model is introduced to shed new light on the effects of symmetry on stochastic gradient desce…

ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling

2025-05-07 · Xiao Wang, Jong-Youl Choi, Takuya Kurihaya, Isaac Lyngaas 외

Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables …

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging

2026-05-12 · Neha Verma, Nikhil Mehta, Shao-Chuan Wang, Naijing Zhang 외 arxiv

Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetting of their general, language-based reasoning abilities. This work i…

Continual Learning

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity

2021-05-11 · Ryan Henderson, Djork-Arné Clevert, Floriane Montanari

Rationalizing which parts of a molecule drive the predictions of a molecular graph convolutional neural network (GCNN) can be difficult. To help, we propose two simple regularization techniques to apply during the traini…

Graph Neural Network

Joint attitude estimation and 3D neural reconstruction of non-cooperative space objects

2025-06-25 · Clément Forray, Pauline Delporte, Nicolas Delaygue, Florence Genin 외

Obtaining a better knowledge of the current state and behavior of objects orbiting Earth has proven to be essential for a range of applications such as active debris removal, in-orbit maintenance, or anomaly detection. 3…

3D ReconstructionAnomaly DetectionNeRF