Owl Opt Library

The entry point of this library is Owl_opt.

Workflow

  1. define a record type 'a t in some module Prms
  2. apply ppx deriver @@deriving prms to type 'a t so that Prms has type Owl_opt.Prms.PT
  3. pass Prms through your favourite algorithm functor to create an optimisation module O
  4. define an objective function f that takes as input your record type 'a t
  5. define initial parameters prms0
  6. define learning rates lr with Owl_opt.Lr
  7. initialise optimisation state s with O.init ~prms0 ()
  8. define stoping criterion function stop: float -> state -> bool
  9. minimise f for the optimisation session with O.min ~stop ~f s

Example

module Prms = struct
   type 'a t = {a: 'a; b: 'a} [@@deriving prms]
end
(* make an Adam optimisation module for the parameter definition Prms *)
module O = Owl_opt.D.Adam.Make (Prms)
(* define the objective function *)
let f _ prms = Owl.Algodiff.D.Maths.(l2norm' (y - ((prms.a *@ x) + prms.b))) 
(* define initial parameters *)
let prms0 = {a = Owl.Algodiff.D.Mat.gaussian 5 5; b = Owl.Algodiff.D.gaussian 5 1} 
(* define fixed learning rate *)
let lr = Owl_opt.Lr.(Fix 1E-4) 
(* initialise an optimisation session *)
let s = O.init ~prms0 ~beta1:0.99 ~beta2:0.999 ~lr () 
(* define stopping criteria: stop when function value is smaller than 1E-4 *)
let stop fv s = fv < 1E-4
(* minimise [f] for session [s] and returns final loss *)
let fv = O.min ~f ~stop s
(* get optimized prms *)
let prms = O.prms s

Important modules

1. Parameters

2. Learning rate

3. Double-precision

4. Single-precision