variance-aware loss

as donto believed on

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

variance-aware loss has 5 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

5 facts·3 predicates·2 sources·1 in dispute

Other facts (4)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

4 facts

Predicate	Value	Ref
Improves Metric	Mae	[2]
Improves Metric	Correlation	[2]
Improves Correlation	null	[1]
Improves Mae	null	[1]

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

5 undated

—

improvesCorrelationblah/watt-activation/part-515

null

—

improvesMAEblah/watt-activation/part-515

null

—

labelblah/watt-activation/512

variance-aware loss

—

improvesMetricblah/watt-activation/512

ex:mae

—

improvesMetricblah/watt-activation/512

ex:correlation

References (2)

2 references

[1]Part 5152 facts
ctx:discord/blah/watt-activation/part-515
[2]5123 facts
ctx:discord/blah/watt-activation/512
- full textwatt-activation-512
  text/plain2 KBdoc:agent/watt-activation-512/b9562690-d0ae-4a31-b0ba-f7ce99f7c320
  Show excerpt
  [2026-03-22 21:20] xenonfun: ⏺ MAE 9.77% — same as plain MSE (9.8%). The weighting doesn't hurt but doesn't help either for this dataset. The early-life predictions are already good because the CHON features naturally separate healthy fr…

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.

variance-aware loss

Other facts (4)

Timeline

References (2)

See also

Keep researching