Delve into the cutting edge of Artificial Intelligence with our dedicated Research Paper section.
High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise Liam Madden, Emiliano Dall’Anese, Stephen Becker; 25(241):1−36, 2024. Abstract Stochastic gradient descent is one of the most common iterative algorithms used in machine learning and its convergence analysis…
![[2409.10139] Towards Explainable Automated Data Quality Enhancement without Domain Knowledge](http://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png "[2409.10139] Towards Explainable Automated Data Quality Enhancement without Domain Knowledge"){kind=logo}
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…
[Submitted on 4 Apr 2024 (v1), last revised 14 Sep 2024 (this version, v2)] View a PDF of the paper titled Uncertainty in Language Models: Assessment through Rank-Calibration, by Xinmeng Huang and 7 other authors View PDF HTML (experimental) Abstract:Language…
[Submitted on 23 May 2024 (v1), last revised 14 Sep 2024 (this version, v2)] View a PDF of the paper titled PuzzleAvatar: Assembling 3D Avatars from Personal Albums, by Yuliang Xiu and 4 other authors View PDF HTML (experimental) Abstract:Generating…
[Submitted on 18 Feb 2024 (v1), last revised 16 Sep 2024 (this version, v2)] View a PDF of the paper titled Discrete Neural Algorithmic Reasoning, by Gleb Rodionov and 1 other authors View PDF HTML (experimental) Abstract:Neural algorithmic reasoning aims…
The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz; 25(242):1−76, 2024. Abstract We study the optimization landscape of deep linear neural networks with square loss. It is known that, under weak…
[Submitted on 28 Oct 2023 (v1), last revised 12 Sep 2024 (this version, v3)] View a PDF of the paper titled Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo in the nonconvex stochastic gradient case, by Martin Chak and Pierre…
[Submitted on 19 Aug 2024 (v1), last revised 13 Sep 2024 (this version, v4)] View a PDF of the paper titled Performance Law of Large Language Models, by Chuhan Wu and 1 other authors View PDF HTML (experimental) Abstract:Guided by…
[Submitted on 3 Jun 2024 (v1), last revised 13 Sep 2024 (this version, v2)] View a PDF of the paper titled Fa\c{c}AID: A Transformer Model for Neuro-Symbolic Facade Reconstruction, by Aleksander Plocharski and 3 other authors View PDF HTML (experimental)…
arXiv:2409.08884v1 Announce Type: cross Abstract: Are general-purpose visual representations acquired solely from synthetic data useful for detecting fake images? In this work, we show the effectiveness of synthetic data-driven representations for synthetic image detection. Upon analysis, we find that vision…
[Submitted on 5 Apr 2024 (v1), last revised 13 Sep 2024 (this version, v5)] Authors:Xinrun Du, Zhouliang Yu, Songyang Gao, Ding Pan, Yuyang Cheng, Ziyang Ma, Ruibin Yuan, Xingwei Qu, Jiaheng Liu, Tianyu Zheng, Xinchen Luo, Guorui Zhou, Wenhu Chen,…
[Submitted on 3 May 2023 (v1), last revised 13 Sep 2024 (this version, v2)] View a PDF of the paper titled Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models, by Qihan Ren and…