adagrad

Documentation

Index

• type AdaGrad
  • func New(c Config) *AdaGrad
  • func (o *AdaGrad) Delta(param *nn.Param) mat.Matrix
  • func (o *AdaGrad) Label() int
  • func (o *AdaGrad) NewSupport(r, c int) *nn.Payload
• type Config
  • func NewConfig(lr, epsilon float64) Config
  • func NewDefaultConfig() Config

Types

type AdaGrad

type AdaGrad struct {
	Config
}

AdaGrad assigns a different learning rate to each parameter using the sum of squares of its all historical gradients. References

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
http://www.jmlr.org/papers/volume12/duchi11a/duchi11a.pdf

func New

func New(c Config) *AdaGrad

func (*AdaGrad) Delta

func (o *AdaGrad) Delta(param *nn.Param) mat.Matrix

func (*AdaGrad) Label

func (o *AdaGrad) Label() int

func (*AdaGrad) NewSupport

func (o *AdaGrad) NewSupport(r, c int) *nn.Payload

type Config

type Config struct {
	gd.MethodConfig
	LR      float64
	Epsilon float64
}

func NewConfig

func NewConfig(lr, epsilon float64) Config

func NewDefaultConfig

func NewDefaultConfig() Config