Files
trueskill-tt/tests/joint_handle.rs
T
logaritmiskandClaude Opus 5 f692906ce4 docs: state what the joint's cost actually scales in
A consumer measured an 8x difference in solve time between two fits over
the same events, the same slices and the same ~2,000 nodes:

  career fit   (gamma = 0)      787 ms
  drifting fit (gamma = 0.15)  6214 ms

Entirely the collapse rule. A competitor with zero drift contributes one
variable however long the history, so a drift-free fit's joint is smaller
than a drifting one's by roughly the slice count — and to factorise, by
its cube. Choosing a drift configuration is therefore also choosing a
query cost, and nothing said so.

Documented on `Joint`, on `Joint::variables` and on `posterior_of`, with
the measurement. `variables()` is named as the number that decides
affordability, since it can be read before committing to a batch.

Also states the thing the consumer proposed as a future optimisation,
because it is already true: an absence is not an appearance, so a
competitor seen in the first and last of a hundred slices contributes two
variables rather than a hundred. The matrix is already as small as the
model allows on that axis.

tests/joint_handle.rs pins the mechanism — ten slices, two competitors,
twenty variables drifting against two at `gamma = 0` — so a change to the
collapse rule cannot quietly remove the property the docs now promise.

Refs #51

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
2026-09-08 19:45:51 +02:00

268 lines
8.4 KiB
Rust

//! `History::joint` factorises once and answers many questions.
//!
//! The contract that matters is *identity*: a `Joint` must return exactly what
//! the one-shot call returns, bit for bit. A faster path that quietly disagreed
//! with the slow one would be worse than no fast path — a caller would get
//! different numbers depending on how many questions they happened to ask.
use smallvec::smallvec;
use trueskill_tt::{
ConstantDrift, ConvergenceOptions, Event, History, InferenceError, Member, Outcome, Team,
UnknownKeys,
};
type H = History<i64, ConstantDrift, trueskill_tt::NullObserver, &'static str>;
fn duel(a: &'static str, b: &'static str, t: i64, sa: f64, sb: f64) -> Event<i64, &'static str> {
Event {
time: t,
teams: smallvec![
Team::with_members([Member::new(a)]),
Team::with_members([Member::new(b)]),
],
outcome: Outcome::scores([sa, sb]),
}
}
fn ranked(a: &'static str, b: &'static str, t: i64) -> Event<i64, &'static str> {
Event {
time: t,
teams: smallvec![
Team::with_members([Member::new(a)]),
Team::with_members([Member::new(b)]),
],
outcome: Outcome::winner(0, 2),
}
}
fn history(unknown: UnknownKeys) -> H {
History::builder()
.mu(0.0)
.sigma(6.0)
.beta(1.0)
.score_sigma(2.0)
.drift(ConstantDrift(0.5))
.unknown_keys(unknown)
.convergence(ConvergenceOptions {
max_iter: 20_000,
epsilon: 1e-13,
alpha: 1.0,
})
.build()
}
/// Several slices, competitors with different last appearances, so `latest`
/// and `at_slice` both have work to do.
fn fitted(unknown: UnknownKeys) -> H {
let mut h = history(unknown);
h.add_events(vec![
duel("a", "b", 1, 5.0, 2.0),
duel("c", "d", 1, 3.0, 3.5),
duel("a", "c", 2, 6.0, 1.0),
duel("b", "d", 3, 4.0, 3.0),
duel("a", "d", 4, 7.0, 2.0),
duel("b", "c", 5, 2.0, 4.0),
])
.unwrap();
let report = h.converge().unwrap();
assert!(report.converged, "fixture must converge");
h
}
const PAIRS: [(&str, &str); 6] = [
("a", "b"),
("a", "c"),
("a", "d"),
("b", "c"),
("b", "d"),
("c", "d"),
];
#[test]
fn a_joint_answers_exactly_what_the_one_shot_call_does() {
let h = fitted(UnknownKeys::Reject);
let joint = h.joint().unwrap();
for (a, b) in PAIRS {
let terms = [(&a, 1.0), (&b, -1.0)];
let one_shot = h.posterior_of(&terms).unwrap();
let cached = joint.posterior_of(&terms).unwrap();
assert_eq!(one_shot.pi(), cached.pi(), "{a} - {b}");
assert_eq!(one_shot.tau(), cached.tau(), "{a} - {b}");
}
}
#[test]
fn a_joint_agrees_at_a_pinned_time_too() {
let h = fitted(UnknownKeys::Reject);
let joint = h.joint().unwrap();
for time in 1..=5 {
for (a, b) in PAIRS {
let terms = [(&a, 1.0), (&b, -1.0)];
let one_shot = h.posterior_of_at(time, &terms);
let cached = joint.posterior_of_at(time, &terms);
match (one_shot, cached) {
(Ok(x), Ok(y)) => {
assert_eq!(x.pi(), y.pi(), "t={time} {a} - {b}");
assert_eq!(x.tau(), y.tau(), "t={time} {a} - {b}");
}
(Err(x), Err(y)) => assert_eq!(x, y, "t={time} {a} - {b}"),
(x, y) => panic!("t={time} {a} - {b}: disagreed on success: {x:?} vs {y:?}"),
}
}
}
}
#[test]
fn a_joint_scores_candidate_matchups_identically() {
let h = fitted(UnknownKeys::Reject);
let joint = h.joint().unwrap();
let (a, b) = ("a", "b");
let target = [(&a, 1.0), (&b, -1.0)];
for (x, y) in PAIRS {
let teams: [&[&&str]; 2] = [&[&x], &[&y]];
let one_shot = h.expected_variance_reduction(&teams, &target).unwrap();
let cached = joint.expected_variance_reduction(&teams, &target).unwrap();
assert_eq!(one_shot, cached, "{x} vs {y}");
}
}
/// The whole point: a competitor appears once per slice, so the joint is over
/// appearances rather than competitors, and a caller sizing a batch needs to
/// know which.
#[test]
fn variables_counts_appearances_not_competitors() {
let h = fitted(UnknownKeys::Reject);
let joint = h.joint().unwrap();
// Four competitors, twelve appearances across five slices, all with
// positive drift between them, so no two collapse.
assert_eq!(joint.variables(), 12);
}
/// How much the collapse is worth, which is the part a caller has to plan
/// around: a drift-free competitor contributes **one** variable however long
/// the history, so the same events at `gamma = 0` and `gamma > 0` differ by
/// roughly the slice count in problem size — and by its cube in solve time.
///
/// Reported by a consumer as an 8x difference in solve time on a ~2,000-node,
/// 76-slice model (787 ms career against 6,214 ms drifting). This pins the
/// mechanism behind that so a change to the collapse rule cannot quietly
/// remove it.
#[test]
fn drift_free_competitors_shrink_the_joint_by_the_slice_count() {
fn variables(gamma: f64) -> usize {
let mut h = History::builder()
.mu(0.0)
.sigma(6.0)
.beta(1.0)
.score_sigma(2.0)
.drift(ConstantDrift(gamma))
.convergence(ConvergenceOptions {
max_iter: 20_000,
epsilon: 1e-13,
alpha: 1.0,
})
.build();
h.add_events(
(1..=10)
.map(|t| duel("a", "b", t, 5.0, 2.0))
.collect::<Vec<_>>(),
)
.unwrap();
let _ = h.converge().unwrap();
h.joint().unwrap().variables()
}
let drifting = variables(0.5);
let career = variables(0.0);
// Two competitors over ten slices: twenty appearances, or two variables.
assert_eq!(drifting, 20);
assert_eq!(career, 2);
assert_eq!(
drifting / career,
10,
"collapse should track the slice count"
);
}
/// With `drift = 0` consecutive appearances are the same latent variable, so
/// the joint is smaller than the appearance count.
#[test]
fn pinned_competitors_collapse_consecutive_appearances() {
let mut h = History::builder()
.mu(0.0)
.sigma(6.0)
.beta(1.0)
.score_sigma(2.0)
.drift(ConstantDrift(0.0))
.convergence(ConvergenceOptions {
max_iter: 20_000,
epsilon: 1e-13,
alpha: 1.0,
})
.build();
h.add_events(vec![
duel("a", "b", 1, 5.0, 2.0),
duel("a", "b", 2, 4.0, 3.0),
duel("a", "b", 3, 6.0, 1.0),
])
.unwrap();
assert!(h.converge().unwrap().converged);
assert_eq!(h.joint().unwrap().variables(), 2);
}
#[test]
fn a_ranked_history_has_no_exact_joint() {
let mut h = history(UnknownKeys::Reject);
h.add_events(vec![duel("a", "b", 1, 5.0, 2.0), ranked("a", "b", 2)])
.unwrap();
let _ = h.converge().unwrap();
assert!(matches!(
h.joint().unwrap_err(),
InferenceError::JointUnavailable { .. }
));
}
#[test]
fn an_empty_history_has_no_joint() {
let h = history(UnknownKeys::Reject);
assert!(matches!(
h.joint().unwrap_err(),
InferenceError::JointUnavailable { .. }
));
}
/// Unknown keys are decided per query, not when the joint is factorised — the
/// factorisation does not depend on the question.
#[test]
fn unknown_keys_are_rejected_per_query() {
let h = fitted(UnknownKeys::Reject);
let joint = h.joint().unwrap();
let (a, z) = ("a", "nobody");
assert!(matches!(
joint.posterior_of(&[(&a, 1.0), (&z, -1.0)]).unwrap_err(),
InferenceError::UnknownKey { .. }
));
// The handle is still usable afterwards.
let b = "b";
assert!(joint.posterior_of(&[(&a, 1.0), (&b, -1.0)]).is_ok());
}
/// Under `Prior`, an unseen competitor is independent of everything in the
/// history, and the cached path must add the same prior variance the one-shot
/// path does.
#[test]
fn unseen_competitors_match_the_one_shot_path() {
let h = fitted(UnknownKeys::Prior);
let joint = h.joint().unwrap();
let (a, z) = ("a", "nobody");
let terms = [(&a, 1.0), (&z, -1.0)];
let one_shot = h.posterior_of(&terms).unwrap();
let cached = joint.posterior_of(&terms).unwrap();
assert_eq!(one_shot.pi(), cached.pi());
assert_eq!(one_shot.tau(), cached.tau());
}