liveBook · Manning

Exponent

As explained in Quantization and Fast Inference

The scale-bearing component of a floating-point representation that determines the magnitude of its significand.

An exponent sets the binary scale of a floating-point value: value = significand × 2^exponent. It moves the representational grid, letting the same significand precision cover different magnitudes; unlike fixed-point, the spacing between values changes with scale. section 2.1

This adaptive range has a computational cost. Floating-point addition requires exponent alignment, and operations require normalization and rounding; floating-point also increases memory traffic and energy costs in inference. section 1.3.1

Table 2.2 Quantize only the mantissa to the nearest multiple of 1/16
True Value
(Approx) mantissa × 2^exp
Quantized mantissa
Reconstructed value
0.01
1.28 × 2⁻⁷
1.3125 × 2⁻⁷
0.01025390625
0.10
1.60 × 2⁻⁴
1.6250 × 2⁻⁴
0.1015625
1.00
1.00 × 2⁰
1.0000 × 2⁰
1.0
3.00
1.50 × 2¹
1.5000 × 2¹
3.0

Toy floating-point examples show how a shared mantissa grid represents small and large values by changing the exponent. section 2.1

How Quantization and Fast Inference covers it

How deep it goes
Defines value as mantissa × 2^exponent, illustrates a toy format numerically, and stops short of IEEE-754 encoding.
Examples
Uses 0.01, 0.10, 1.00, and 3.00 in a toy float to show exponent-dependent spacing.
What you can do after
Understand how an exponent moves the representational grid to provide scale-dependent resolution.
How it connects
Ties exponents to significands, floating-point representation, fixed-point grids, and quantization.

Also explained in

Compare how 6 books explain exponent →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Quantization and Fast Inference. The section links point to the parts of the book it draws on.