Delve into the cutting edge of Artificial Intelligence with our dedicated Research Paper section.
![[1809.04564] On the Generalization of Stochastic Gradient Descent with Momentum](http://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png "[1809.04564] On the Generalization of Stochastic Gradient Descent with Momentum"){kind=logo}
[Submitted on 12 Sep 2018 (v1), last revised 15 Jan 2024 (this version, v3)] Download a PDF of the paper titled On the Generalization of Stochastic Gradient Descent with Momentum, by Ali Ramezani-Kebrya and 4 other authors Download PDF Abstract:While…
Concentration analysis of multivariate elliptic diffusions Lukas Trottner, Cathrine Aeckerle-Willems, Claudia Strauch; 24(106):1−38, 2023. Abstract We prove concentration inequalities and associated PAC bounds for both continuous- and discrete-time additive functionals for possibly unbounded functions of multivariate, nonreversible diffusion processes. Our…
A Permutation-Free Kernel Independence Test Shubhanshu Shekhar, Ilmun Kim, Aaditya Ramdas; 24(369):1−68, 2023. Abstract In nonparametric independence testing, we observe i.i.d.\ data $\{(X_i,Y_i)\}_{i=1}^n$, where $X \in \mathcal{X}, Y \in \mathcal{Y}$ lie in any general spaces, and we wish to test…
Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities Brian R. Bartoldson, Bhavya Kailkhura, Davis Blalock; 24(122):1−77, 2023. Abstract Although deep learning has made great progress in recent years, the exploding economic and environmental costs of training neural networks are becoming unsustainable.…
On the Dynamics Under the Unhinged Loss and Beyond Xiong Zhou, Xianming Liu, Hanzhang Wang, Deming Zhai, Jiangjunjun, Xiangyang Ji; 24(376):1−62, 2023. Abstract Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier…
Pervasive use of social media has become the emerging source for real-time information (like images, text, or both) to identify various events. Despite the rapid growth of image and text-based event classification, the state-of-the-art (SOTA) models find it challenging to…
To sample from a general target distribution $p_*\propto e^{-f_*}$ beyond the isoperimetric condition, Huang et al. (2023) proposed to perform sampling through reverse diffusion, giving rise to Diffusion-based Monte Carlo (DMC). Specifically, DMC follows the reverse SDE of a diffusion…
Set-valued Classification with Out-of-distribution Detection for Many Classes Zhou Wang, Xingye Qiao; 24(375):1−39, 2023. Abstract Set-valued classification, a new classification paradigm that aims to identify all the plausible classes that an observation belongs to, improves over the traditional classification paradigms…
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.…
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 17 Nov 2023] Download a PDF of the paper titled The possibility of making $\$138,000$ from shredded banknote pieces using computer vision, by Chung To Kong Download PDF Abstract:Every country must dispose of old banknotes. At the Hong…
Speech has long been a barrier to effective communication and connection, persisting as a challenge in our increasingly interconnected world. This research paper introduces a transformative solution to this persistent obstacle an end-to-end speech conversion framework tailored for Hindi-to-English translation,…