LVL 01SK
Project overview
MATHEMATICS & VISUAL EXPLANATION

Federated Averaging

Derive the core equations slowly, attach every symbol to code, and verify the result with small numerical examples before scaling the implementation.

How to study the mathematics

Read each chapter in four passes: intuition, symbols, derivation, and implementation. Recalculate the worked example by hand. Then change one number and predict the direction of the result before running code.

01
FIRST-PRINCIPLES DERIVATION

FedAvg

Intuition before notation

Federated averaging combines client models in proportion to the amount of local evidence they represent.

Loading equation…

Symbol dictionary

w_t
global parameters
S_t
selected clients
n_k
client sample count
w^(k)
locally trained parameters

Derive it one move at a time

  1. 1

    Broadcast the same global state.

  2. 2

    Train selected clients locally.

  3. 3

    Count the examples represented by each update.

  4. 4

    Normalize client weights by participating sample count.

  5. 5

    Sum every parameter tensor with those weights.

INPUTKnown quantities
TRANSFORMFedAvg
CHECKValue, shape, invariant

Worked numerical example

Clients with 20 and 80 samples produce scalar parameters 1 and 3. The weighted result is 0.2*1+0.8*3=2.6, not the unweighted mean 2.

Translate the derivation into code

  • Clone state dictionaries before local training.
  • Aggregate every key with identical dtype and shape.
  • Test equivalence with centralized averaging for a controlled case.
02
FIRST-PRINCIPLES DERIVATION

Non-IID data

Intuition before notation

Non-IID data is a transformation whose meaning comes from its domain, codomain, objective, and invariants. The equation is useful only when every symbol maps to a concrete tensor, state, or measurement.

Loading equation…

Symbol dictionary

x,y
input and target
f_theta
parameterized transformation
ell
data objective
Omega
regularizer
lambda
regularization weight

Derive it one move at a time

  1. 1

    Specify the input representation.

  2. 2

    Define the parameterized transformation.

  3. 3

    Choose a loss connected to desired behavior.

  4. 4

    Average over the training evidence.

  5. 5

    Add explicit inductive bias or constraints.

INPUTKnown quantities
TRANSFORMNon-IID data
CHECKValue, shape, invariant

Worked numerical example

For a one-parameter predictor f(x)=theta*x with x=2, y=6, squared loss is (2theta-6)^2. The minimum without regularization is theta=3.

Translate the derivation into code

  • Give every axis a semantic name.
  • Implement a scalar reference first.
  • Compare optimized output and gradients against the reference.
03
FIRST-PRINCIPLES DERIVATION

Communication rounds

Intuition before notation

Communication rounds is a transformation whose meaning comes from its domain, codomain, objective, and invariants. The equation is useful only when every symbol maps to a concrete tensor, state, or measurement.

Loading equation…

Symbol dictionary

x,y
input and target
f_theta
parameterized transformation
ell
data objective
Omega
regularizer
lambda
regularization weight

Derive it one move at a time

  1. 1

    Specify the input representation.

  2. 2

    Define the parameterized transformation.

  3. 3

    Choose a loss connected to desired behavior.

  4. 4

    Average over the training evidence.

  5. 5

    Add explicit inductive bias or constraints.

INPUTKnown quantities
TRANSFORMCommunication rounds
CHECKValue, shape, invariant

Worked numerical example

For a one-parameter predictor f(x)=theta*x with x=2, y=6, squared loss is (2theta-6)^2. The minimum without regularization is theta=3.

Translate the derivation into code

  • Give every axis a semantic name.
  • Implement a scalar reference first.
  • Compare optimized output and gradients against the reference.
04
FIRST-PRINCIPLES DERIVATION

Optimization and parameter updates

Intuition before notation

objective and gradient update is a transformation whose meaning comes from its domain, codomain, objective, and invariants. The equation is useful only when every symbol maps to a concrete tensor, state, or measurement.

Loading equation…

Symbol dictionary

x,y
input and target
f_theta
parameterized transformation
ell
data objective
Omega
regularizer
lambda
regularization weight

Derive it one move at a time

  1. 1

    Specify the input representation.

  2. 2

    Define the parameterized transformation.

  3. 3

    Choose a loss connected to desired behavior.

  4. 4

    Average over the training evidence.

  5. 5

    Add explicit inductive bias or constraints.

INPUTKnown quantities
TRANSFORMOptimization and parameter updates
CHECKValue, shape, invariant

Worked numerical example

For a one-parameter predictor f(x)=theta*x with x=2, y=6, squared loss is (2theta-6)^2. The minimum without regularization is theta=3.

Translate the derivation into code

  • Give every axis a semantic name.
  • Implement a scalar reference first.
  • Compare optimized output and gradients against the reference.
05
FIRST-PRINCIPLES DERIVATION

Probability, normalization, and calibration

Intuition before notation

Softmax converts relative logits into positive normalized probabilities while temperature controls how strongly differences are expressed.

Loading equation…

Symbol dictionary

z_i
logit for outcome i
m
maximum logit
tau
temperature
p_i
normalized probability

Derive it one move at a time

  1. 1

    Divide logits by temperature.

  2. 2

    Find the maximum scaled logit.

  3. 3

    Subtract it without changing probability ratios.

  4. 4

    Exponentiate the shifted values.

  5. 5

    Divide by their sum.

INPUTKnown quantities
TRANSFORMProbability, normalization, and calibration
CHECKValue, shape, invariant

Worked numerical example

Logits [1000,999] overflow naively. Subtracting 1000 gives [0,-1], whose probabilities are approximately [0.731,0.269].

Translate the derivation into code

  • Reduce maximum with keepdims.
  • Use the same axis for maximum and sum.
  • Test translation invariance by adding a constant to every logit.
06
FIRST-PRINCIPLES DERIVATION

Evaluation uncertainty and error bars

Intuition before notation

A reported metric is an estimate from finite evidence. Uncertainty separates stable improvement from sampling noise.

Loading equation…

Symbol dictionary

x_i
per-example or per-run measurement
x-bar
sample mean
s
sample standard deviation
n
independent observations

Derive it one move at a time

  1. 1

    Choose the independent unit.

  2. 2

    Compute one measurement per unit.

  3. 3

    Estimate mean and sample variance.

  4. 4

    Convert variation into standard error.

  5. 5

    Report an interval with assumptions or use bootstrap resampling.

INPUTKnown quantities
TRANSFORMEvaluation uncertainty and error bars
CHECKValue, shape, invariant

Worked numerical example

Five seeded scores with mean 0.80 and standard deviation 0.04 have SE about 0.0179, giving a rough 95% interval 0.765 to 0.835.

Translate the derivation into code

  • Store per-example and per-seed values, not only the average.
  • Use stratified or paired intervals when the design requires them.
  • Never treat correlated tokens or timesteps as independent runs.