At this seminal we’ll discuss stochastic optimisation methods. Those methods are a key technique to learn many machine learning models on big datasets. Firstly, we’ll discuss classical stochastic gradients descent: theoretical results and issues of method. Secondly, we’ll talk about variance reduction techniques used to improve convergence rate (AdaGrad, SVRG, Adam). Finally, we’ll cover practicals aspects: how to implement algorithm in distributed settings (multi-CPU/GPU learning) and what computations problems one will face.
Speaker: Vasily Ershov.
Presentation language: Russian.
Date and time: February 14th, 20:00-21:30.
Location: Times, room 405.
Videos from seminars will be available at http://bit.ly/MLJBSeminars
- About seminars
6 June 2019Public speaking master class
30 May 2019PolyTree framework for tree ensemble analysis
23 May 2019Aggregation of pairwise comparisons with reduction of biases
16 May 2019Recommendation system for writing texts in a specific domain area
25 April 2019Topic modeling of a news stream