The keynote talk from: Analysis of adaptive stochastic gradient and MCMC algorithms
Organiser: Sotirios Sabanis (The Alan Turing Institute and The University of Edinburgh)
Stochastic approximations (including stochastic gradient methods) are online optimization procedures which track key parameters of interest of data streams even in cases of changing dynamics. Their adaptive nature makes them highly applicable in data procession & machine learning and thus they are widely used in industry. Similarly, the importance of MCMC algorithms in Data Science has grown exponentially in the last decade or so.
Despite all this success, significant technical & theoretical challenges remain which impede the practical implementation of such state-of-the-art algorithms to more diverse sets of real world problems, typically of very high dimension. Leading experts from the field of stochastic approximations, MCMC algorithms, Bayesian inference and probability theory will gather to discuss these issues
About the Turing
The Alan Turing Institute, headquartered in the British Library, London, was created as the national institute for data science in 2015. In 2017, as a result of a government recommendation, we added artificial intelligence to our remit.
The Institute is named in honour of Alan Turing (23 June 1912 – 7 June 1954), whose pioneering work in theoretical and applied mathematics, engineering and computing are considered to be the key disciplines comprising the fields of data science and artificial intelligence.
To learn more about what we do, watch our new video on 'What is The Alan Turing Institute'
[ Ссылка ]
