Talk: Theoretical Aspects of Gradient Methods in Deep Learning

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=x1IhcWfc3Ao


Duration: 20:41
437 views
17

Talk: Theoretical Aspects of Gradient Methods in Deep Learning by Jian Li of Tsinghua University.

Learn more about the 2021 MSR Asia Theory Workshop:
https://www.microsoft.com/en-us/research/event/2021-msr-asia-theory-workshop/



Other Videos By Microsoft Research


2022-01-24Panel: Large-scale neural platform models: Opportunities, concerns, and directions
2022-01-24Panel: Causal ML Research at Microsoft
2022-01-24Panel: The future of search and recommendation: Beyond web search
2022-01-24Panel: Space systems and next-generation telecommunications
2022-01-24Panel: Cloud Intelligence/AIOps across academia and industry
2022-01-24Panel: Generalization in reinforcement learning
2022-01-24Panel: Advancing carbon capture and energy management
2022-01-20Unsupervised Speech Enhancement
2022-01-20Developing a Brain-Computer Interface Based on Visual Imagery
2022-01-04Panel: Theory Research in Big Data Era
2022-01-04Talk: Theoretical Aspects of Gradient Methods in Deep Learning
2022-01-04SysSieve: Extracting Actionable Insights from Unstructured Text
2022-01-03Fourier Feature Networks and Neural Volume Rendering
2021-12-20DIABLo: a Deep Individual-Agnostic Binaural Localizer
2021-12-16Our Genomes, Our Selves?
2021-12-01A law of robustness and the importance of overparametrization in deep learning
2021-11-29Research for Industries (RFI) Lecture Series: Steven K. Frey
2021-11-24Research for Industries (RFI) Lecture Series: Matthew Realff & Christopher Jones
2021-11-23On Race and Technoculture
2021-11-08Acrylic, metal & a means of preparation: Imagining & living Black life beyond the surveillance state
2021-11-01FastNeRF: High-Fidelity Neural Rendering at 200FPS [Extended]