DeepForgeby svx

0/5730 solved

← All interview tracks

MLE · new gradsLinear algebra · optimization · probability

Google · Machine Learning Engineer

Math-heavy screens in the Google style: matrix decompositions, eigen-computations, convex optimization steps, and probability foundations.

3 phases · 26 problems · 26 unique

Start timed mock5 problems · 4 min each

Your progress

0/26 · 0%

Continue track · Matrix Multiplication

1Warm-up

0/8

Matrix Multiplication
la-001Linear Algebra
Easy
Vector Dot Product
la-004Linear Algebra
Easy
L2 Vector Norm
la-006Linear Algebra
Easy
Cosine Similarity of Vectors
la-025Linear Algebra
Medium
Numerical Derivative
ca-001Calculus
Easy
Exponential LR Schedule
op-005Optimization
Easy
Expected Value
pr-002Probability
Easy
Mean
st-001Statistics
Easy

2Core

0/10

Eigenvector Check
la-040Linear Algebra
Medium
Condition Number via 1-Norms
la-042Linear Algebra
Medium
Covariance Matrix from Data
la-074Linear Algebra
Medium
Eigenvalues 2x2
la-083Linear Algebra
Medium
Ridge Regression Solve
la-125Linear Algebra
Medium
Gradient Descent
op-001Optimization
Medium
Momentum Optimizer
op-003Optimization
Medium
Generic Adam Update
op-010Optimization
Medium
Cosine Annealing Learning Rate
op-015Optimization
Medium
Markov Chain One-Step
pr-037Probability
Medium

3Hard

0/8

Reduced Row Echelon Form
la-045Linear Algebra
Hard
LU Decomposition (Doolittle)
la-047Linear Algebra
Hard
Gram-Schmidt Orthonormalization
la-049Linear Algebra
Hard
Power Iteration Dominant Eigenvalue
la-050Linear Algebra
Hard
Spectral Norm by Power Iteration
la-132Linear Algebra
Hard
Ridge Regression Closed Form
ml-013ML Fundamentals
Hard
Mini-Batch SGD for Linear Regression
op-002Optimization
Hard
Adam Optimizer
op-004Optimization
Hard