cs231n-notes-Lecture-7：各種優化方法介紹與比較

Lecture-7 Training Neural Networks

Optimization

SGD

• Cons
  1. Very slow progress along shallow dimension, jitter along steep direction.

     

     2. local minima or saddle point. Saddle points are much more common in high dimension.

     

  2. Gradients come from minibatches, so they can be noisy!

SGD + Momentum

Nesterov Momentum

AdaGrad

• step size becomes smaller and smaller because grad_squared is always increasing.
• the gradient becomes smaller in the waggling dimension
• not common: Slow, get stuck easily

RMSProp

• decay_rate: commonly 0.9 or 0.99
• Slove the problem that Adagrad always slow down the movement in all dimensions : only work in some dimesions whose gradients are large.

Adam

• Sort of like RMSProp with momentum
• Bias correction is used to avoid it moves large distance at the very first step.

Learning rate decay

• common in SGD but not in Adam.
• draw the loss curve and think if it’s needed.

Second-order Optimization

• Quasi-Newton methods (BGFS most popular):

• instead of inverting the Hessian (O(n^3)), approximate
• inverse Hessian with rank 1 updates over time (O(n^2) each).

• L-BFGS (Limited memory BFGS):

Does not form/store the full inverse Hessian.

• Usually works very well in full batch, deterministic mode i.e. if you have a single, deterministic f(x) then L-BFGS will probably work very nicely
• Does not transfer very well to mini-batch setting. Give bad results. Adapting L-BFGS to large-scale, stochastic setting is an active area of research.

Model Ensembles

1. Train multiple independent models
2. At test time average their results

Enjoy 2% extra performance

Tips and Tricks

• Instead of training independent models, use multiple snapshots of a single model during training!

Loshchilov and Hutter, “SGDR: Stochastic gradient descent with restarts”, arXiv 2016 Huang et al, “Snapshot ensembles: train 1, get M for free”, ICLR 2017

Improve single-model performance

Regularization

• Add term to loss

  

• Dropout (two explanations)
  • Forces the network to have a redundant representation; Prevents co-adaptation of features
  • Dropout is training a large ensemble of models (that share parameters).
• Data augmentation
  • Horizontal Flips
  • Random crops and scales
  • Color Jitter
  • translation
  • rotation
  • stretching
  • shearing
  • lens distortions
• DropConnect

Wan et al, “Regularization of Neural Networks using DropConnect”, ICML 2013

• Fractional Max Pooling

Graham, “Fractional Max Pooling”, arXiv 2014

• Stochastic Depth

Huang et al, “Deep Networks with Stochastic Depth”, ECCV 2016