aNotation

Karthik Thiagarajan

1. CommonScalars: x1,x2,y1,y2,z2,z2,a,b,𝛼,𝛽 Column vector:x∈Rd x=a

x1

⋮

xd

Row vector: x∈Rd xT=a

x1

⋯

xd

Matrix: X∈Rd×n 2. Labeled Dataset D={(x1,y1),⋯,(xn,yn)} 2.1. Data-matrix X∈Rd×n • d→number of features• n→number of data-points X=a

|		|
x1	⋯	xn
|		|

2.2. Data-pointxi∈Rd 2.3. Label setFor binary classification, the label set could be {0,1} or {1,-1}. 2.4. True Labels y∈{0,1}ory∈{1,-1}2.5. Predicted Labels y∈{0,1}ory∈{1,-1} 2.6. Label Vector y∈{0,1}nor y∈{1,-1}n where y=a

y1

⋮

yn