Equation 1 · How Do We Know a Compressed Model Still Works?
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This equation states an equality: the expressions on both sides have the same value under the article’s assumptions. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol i
i appears in the bound of this sum. The bound states where the repeated operation starts, ends, or which values it includes.
Symbol n
n appears in the bound of this sum. The bound states where the repeated operation starts, ends, or which values it includes.
Symbol w_i
is an input to the expression that computes the quantity on the left.
=
The expressions on both sides represent the same quantity under the stated assumptions.
See an illustrated explanation →subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
superscript
A raised number can be a power. When it is a label or bound, it selects a case or the upper limit of a sum; the formula’s structure distinguishes these uses.
See an illustrated explanation →Starting index or lower bound: i=1
This label says where the repeated addition, multiplication, or accumulation starts. Read its value or condition together with the article’s description of the index.
Ending index or upper bound: n
This label says where the repeated addition, multiplication, or accumulation stops. It sets the last term or end of the range.
How to interpret it
Read it with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
An aggregate benchmark score is a weighted average over items or tasks: . where is accuracy, or another per-task quality measure, on task i , and is that task’s share of the total, with the weights summing to one. The arithmetic makes the trap explicit: S can be almost unchanged by compression even when some single collapses, provided for that task is small relative to the rest, or provided a rise elsewhere offsets the fall. A single published number, ninety-eight point six percent of baseline, or a small perplexity increase, cannot by construction distinguish “compression cost nothing” from “compression cost a great deal on one task nobody weighted…
Read the full surrounding passage
An aggregate benchmark score is a weighted average over items or tasks: . where is accuracy, or another per-task quality measure, on task i , and is that task’s share of the total, with the weights summing to one. The arithmetic makes the trap explicit: S can be almost unchanged by compression even when some single collapses, provided for that task is small relative to the rest, or provided a rise elsewhere offsets the fall. A single published number, ninety-eight point six percent of baseline, or a small perplexity increase, cannot by construction distinguish “compression cost nothing” from “compression cost a great deal on one task nobody weighted heavily.” Both produce the same S .
For background, read the article’s source list.
Return to How Do We Know a Compressed Model Still Works?