Coralia Cartis

Tuesday 12th February 2019

Time: 4.00pm

Ground Floor Seminar Room

25 Howland Street, London, W1T 4JG

Optimization algorithms for machine learning

Optimization is a key component of machine learning application, as it helps with training of (neural net, nonconvex) models and parameter tuning. Classical optimization methods are challenged by the scale of machine learning applications and the lack of /cost of full derivatives, as well as the stochastic nature of the problem. On the other hand, the simple approaches that the machine learning community uses need improvement. Here we try to merge the two perspectives and adapt the strength of classical optimization techniques to meet the challenges of data science applications: from deterministic to stochastic problems, from small to large scale.