paper-with-me

홈 › Papers

Deep Learning as the Disciplined Construction of Tame Objects

2025-09-22 · Gilles Bareilles, Allen Gehret, Johannes Aspman, Jana Lepšová, Jakub Mareček arxiv

One can see deep-learning models as compositions of functions within the so-called tame geometry. In this expository note, we give an overview of some topics at the interface of tame geometry (also known as o-minimality), optimization theory, and deep learning theory and practice. To do so, we gradually introduce the concepts and tools used to build convergence guarantees for stochastic gradient descent in a general nonsmooth nonconvex, but tame, setting. This illustrates some ways in which tame geometry is a natural mathematical framework for the study of AI systems, especially within Deep Learning.

📄 PDF Abstract BibTeX arXiv:2509.18025

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DiscoverDCP: A Data-Driven Approach for Construction of Disciplined Convex Programs via Symbolic Regression

2025-12-03 · Sveinung Myhre arxiv

We propose DiscoverDCP, a data-driven framework that integrates symbolic regression with the rule sets of Disciplined Convex Programming (DCP) to perform system identification. By enforcing that all discovered candidate …

Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements

2025-11-23 · Juan Romero, Qiang Fu, Matteo Ravasi, Wolfgang Heidrich arxiv

Hyperspectral image reconstruction from a compressed measurement is a highly ill-posed inverse problem. Current data-driven methods suffer from hallucination due to the lack of spectral diversity in existing hyperspectra…

Image ReconstructionBayesian Inference

Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic Gradient Noise and Localizing Taming

2026-06-03 · Yiwei Zhou, Ziheng Chen arxiv

Stochastic gradient Langevin algorithms often use tamed denominators to stabilize superlinear drifts. This paper shows that when the denominator depends on the current stochastic gradient, the transformed update can have…

Limitations of Data-Driven Spectral Reconstruction -- Optics-Aware Analysis and Mitigation

2024-01-08 · Qiang Fu, Matheus Souza, Eunsue Choi, Suhyun Shin 외

Hyperspectral imaging empowers machine vision systems with the distinct capability of identifying materials through recording their spectral signatures. Recent efforts in data-driven spectral reconstruction aim at extrac…

Data AugmentationSpectral Reconstruction

DMML-Net: Deep Metametric Learning for Few-Shot Geographic Object Segmentation in Remote Sensing Imagery

2021-10-08 · IEEE Transactions on Geoscience and Remote Sensing 2021 10 · Bing Wang, Zhirui Wang, Xian Sun, Hongqi Wang 외

Geographic object segmentation is a fundamental yet challenging problem for remote sensing image interpretation. The prevalent paradigm to solve this problem is to train deep neural networks on massive labeled samples. A…

Metric LearningSegmentationSemantic Segmentation