Struct Config 

pub struct Config {

    pub population: usize,
    pub max_depth: usize,
    pub max_epochs: usize,
    pub learning_rate: f64,
    pub lambda_complexity: f64,
    pub lambda_sparsity: f64,
    pub lambda_parsimony: f64,
    pub tau_start: f64,
    pub tau_end: f64,
    pub temp_schedule: TempSchedule,
    pub seed: u64,
    pub top_k: usize,
    pub backend: Backend,
}

Configuration for a crate::Discoverer run.

Construct with Config::default and adjust via the builder methods, e.g.

use phop_core::Config;
let cfg = Config::default().population(256).max_depth(10).max_epochs(2_000);
assert_eq!(cfg.population, 256);

Fields

population: usize

Number of candidate trees evaluated jointly.

max_depth: usize

Maximum depth of candidate EML trees.

max_epochs: usize

Maximum number of optimization epochs.

learning_rate: f64

Adam learning rate.

lambda_complexity: f64

Weight on the complexity penalty in the multi-objective loss.

lambda_sparsity: f64

Weight on the sparsity penalty (pressure toward the constant 1).

lambda_parsimony: f64

Weight on the parsimony (depth) penalty.

tau_start: f64

Initial Gumbel-Softmax temperature.

tau_end: f64

Final Gumbel-Softmax temperature.

temp_schedule: TempSchedule

Temperature annealing schedule.

seed: u64

RNG seed for reproducibility.

top_k: usize

Number of solutions to keep on the Pareto front.

backend: Backend

Compute backend for constant fitting (CPU by default; CUDA when built and available).

Implementations

impl Config

pub fn population(self, p: usize) -> Self

Set the population size.

pub fn max_depth(self, d: usize) -> Self

Set the maximum tree depth.

pub fn max_epochs(self, n: usize) -> Self

Set the maximum number of epochs.

pub fn learning_rate(self, lr: f64) -> Self

Set the Adam learning rate.

pub fn seed(self, s: u64) -> Self

Set the RNG seed.

pub fn top_k(self, k: usize) -> Self

Set the number of Pareto solutions to keep.

pub fn backend(self, backend: Backend) -> Self

Set the compute backend for constant fitting.

pub fn temperature(&self, t: f64) -> f64

Temperature at training progress t in [0, 1] under the configured schedule.

Trait Implementations

impl Clone for Config

fn clone(&self) -> Config

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Config

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Config

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Config

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Config

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.