Page 1 of 1
SGD with momentum is a variation of the SGD where we use the gradient at the previous iteration in the current update. T
Posted: Mon May 02, 2022 4:14 pm
by answerhappygod
- Sgd With Momentum Is A Variation Of The Sgd Where We Use The Gradient At The Previous Iteration In The Current Update T 1 (70.8 KiB) Viewed 48 times
SGD with momentum is a variation of the SGD where we use the gradient at the previous iteration in the current update. The update with momentum is as follows: al aL (wt)) - (w(t-1)) aw дw L(w) is the objective function as shown in the figure below, and a, y > 0 are the learning rates. Assume for iteration t= 0 and t=-1, we set w(t) = wo as the initial guess. w(t+1) w) 8 6 4 Figure 1: Graph of objective func- tion L 2 0 -15 -10 -5 10 15 Answer the following with justification: a) Assuming that wo = -8 (the flat region). Discuss if the basic SGD (y = 0 ) algorithm terminate at the minimum? Why? (Why not?) b) Assuming that wo = -6 (in a sloped region). Discuss if the basic SGD (y = 0 ) algorithm terminate at the minimum? Why? (Why not?) c) Assuming that wo = -8 (the flat region). Discuss if the SGD with momentum (y > 0 ) algorithm terminate at the minimum? Why? (Why not?) d) Assuming that wo = -6 (in a sloped region). Discuss if the SGD with momentum (y > 0) terminate at the minimum? Why? (Why not?)