← All parts of this equation

Equation 1 · Part 4 · How Do We Know a Compressed Model Still Works?

Symbol w_i

S=∑i=1nwi aiS = \sum_{i=1}^{n} w_i \, a_i
wiw_i

What this part means

wiw_i is an input to the expression that computes the quantity on the left.

Its job in the formula

wiw_i is an input to the expression that computes the quantity on the left.

The passage around this formula

An aggregate benchmark score is a weighted average over items or tasks: S=∑i=1nwi aiS = \sum_{i=1}^{n} w_i \, a_i. where aia_i is accuracy, or another per-task quality measure, on task i , and wiw_i 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 aia_i collapses, provided wiw_i for that task is small relative to the rest, or provided a rise elsewhere offsets the fall. A…

Read this part in the article →

Learn the underlying idea

A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? guide →

See this notation across published equations →

The article lists its research sources here.