19618

Video URL

https://simons.berkeley.edu/talks/fundamental-limits-learning-data-driven-problems

Fundamental Limits Of Learning In Data-Driven Problems

(2022). Fundamental Limits Of Learning In Data-Driven Problems. The Simons Institute for the Theory of Computing. https://simons.berkeley.edu/talks/fundamental-limits-learning-data-driven-problems

Fundamental Limits Of Learning In Data-Driven Problems. The Simons Institute for the Theory of Computing, Feb. 11, 2022, https://simons.berkeley.edu/talks/fundamental-limits-learning-data-driven-problems 

          @misc{ scivideos_19618,
            doi = {},
            url = {https://simons.berkeley.edu/talks/fundamental-limits-learning-data-driven-problems},
            author = {},
            keywords = {},
            language = {en},
            title = {Fundamental Limits Of Learning In Data-Driven Problems},
            publisher = {The Simons Institute for the Theory of Computing},
            year = {2022},
            month = {feb},
            note = {19618 see, \url{https://scivideos.org/Simons-Institute/19618}}
          }
Yanjun Han (Simons Institute)
Talk number19618
Source RepositorySimons Institute
Subject

Abstract

What is the best we can do with the amount of data at our disposal with a given learning task? Modern learning problems---with a modest amount of data or subject to data processing constraints---frequently raise the need to understand the fundamental limits and make judicious use of the available small or imperfect data. This talk will cover several examples of learning where exploiting the key structure, as well as optimally trading between real-world resources, are vital to achieve statistical efficiency.