feat: factorise the joint once with History::joint
`posterior_of`, `posterior_of_at` and `expected_variance_reduction` each
built the joint precision matrix, factorised it, asked one question and
threw it away. The factorisation is O(n^3) in the history's appearances
and depends only on the fit, so a caller asking about every pair in a
standings table, every cell in a grid, or every candidate in an
active-learning sweep paid for the same factorisation once per question.
`History::joint()` returns a `Joint` handle that pays it once. Measured
on 1976 appearances, 90 queries: 68.4s one-shot against 745ms factorise
plus 93ms of queries — 81.6x, with bit-identical answers. Per query,
Criterion at 480 appearances: 9.0ms one-shot against 48us cached, 187x.
The handle borrows the history, which is what makes it correct with no
invalidation logic: the borrow checker forbids adding events or refitting
while it is alive, so there is no window in which the factorisation could
describe a fit that no longer exists. It also makes the lifetime of the
n^2 factor explicit rather than parking it in the history forever — at
4000 appearances that is 128MB, which is not something to cache silently.
Every question the joint answers turns out to be a bilinear form,
c^T A^-1 a = (L^-1 c) . (L^-1 a)
so no caller ever needs L^-1 c itself. Replacing the general solve with a
forward substitution drops the back substitution as wasted work, halving
a query, and removes a failure mode: a variance as `c . (A^-1 c)` is a
difference of products that can round negative, where `|L^-1 c|^2` is a
sum of squares and cannot.
The one-shot calls are unchanged in cost and now delegate to the handle,
so the two paths cannot drift apart. tests/joint_handle.rs asserts they
agree bit for bit, including at pinned times, under UnknownKeys::Prior,
and across candidate matchups.
Refs #51
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
This commit is contained in:
@@ -0,0 +1,220 @@
|
||||
//! `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);
|
||||
}
|
||||
|
||||
/// 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());
|
||||
}
|
||||
Reference in New Issue
Block a user