โจทย์
Adam keeps two moving averages per weight, of the gradient (m) and of the squared gradient (v), and uses them to give each weight its own step size.
Start with m = 0 and v = 0 for every weight. For each step t = 1, 2, 3, … with gradient g:
- m ← beta1 × m + (1 - beta1) × g
- v ← beta2 × v + (1 - beta2) × g²
- m̂ = m / (1 - beta1ᵗ) and v̂ = v / (1 - beta2ᵗ) (bias correction)
- w ← w - learning_rate × m̂ / (√v̂ + epsilon)
Implement adam_steps(gradients, weights, learning_rate, beta1, beta2, epsilon), applying one update per row of gradients, in order.
Input
gradients: One row per step; each row has one gradient per weight.
weights: The starting weights.
learning_rate, beta1, beta2, epsilon: Adam's hyperparameters (commonly 0.001, 0.9, 0.999 and 0.00000001).
Output
Return the weights after all steps.
เงื่อนไข
0 ≤ steps ≤ 1,000, 1 ≤ weights ≤ 100
0 < learning_rate ≤ 1, 0 ≤ beta1, beta2 < 1, 0 < epsilon ≤ 0.001
-100 ≤ each value ≤ 100
ตัวอย่าง
อินพุต:
beta1 = 0.9
beta2 = 0.999
epsilon = 1.0e-08
weights = [1.0]
gradients = [
[2.0]
]
learning_rate = 0.1
ผลลัพธ์ที่คาดหวัง:
expected = [0.9]อินพุต:
double beta1 = 0.9;
double beta2 = 0.999;
double epsilon = 1.0e-08;
std::vector<double> weights = {1.0};
std::vector<std::vector<double>> gradients = {
{2.0}
};
double learning_rate = 0.1;
ผลลัพธ์ที่คาดหวัง:
std::vector<double> expected = {0.9};อินพุต:
double beta1 = 0.9;
double beta2 = 0.999;
double epsilon = 1.0e-08;
double[] weights = new double[] {1.0};
double[][] gradients = new double[][] {
new double[] {2.0}
};
double learning_rate = 0.1;
ผลลัพธ์ที่คาดหวัง:
double[] expected = new double[] {0.9};คำอธิบาย
m = 0.1 × 2 = 0.2 and v = 0.001 × 4 = 0.004. Bias correction gives m̂ = 0.2 / 0.1 = 2 and v̂ = 0.004 / 0.001 = 4, so the step is 0.1 × 2 / √4 = 0.1: w = 0.9. On its first step Adam moves each weight by about the learning rate, whatever the gradient's size.
อินพุต:
beta1 = 0.9
beta2 = 0.999
epsilon = 1.0e-08
weights = [0.0, 0.0]
gradients = [
[100.0, 0.01]
]
learning_rate = 0.01
ผลลัพธ์ที่คาดหวัง:
expected = [-0.01, -0.01]อินพุต:
double beta1 = 0.9;
double beta2 = 0.999;
double epsilon = 1.0e-08;
std::vector<double> weights = {0.0, 0.0};
std::vector<std::vector<double>> gradients = {
{100.0, 0.01}
};
double learning_rate = 0.01;
ผลลัพธ์ที่คาดหวัง:
std::vector<double> expected = {-0.01, -0.01};อินพุต:
double beta1 = 0.9;
double beta2 = 0.999;
double epsilon = 1.0e-08;
double[] weights = new double[] {0.0, 0.0};
double[][] gradients = new double[][] {
new double[] {100.0, 0.01}
};
double learning_rate = 0.01;
ผลลัพธ์ที่คาดหวัง:
double[] expected = new double[] {-0.01, -0.01};คำอธิบาย
The gradients differ by a factor of 10,000, yet both weights move by about 0.01, to [-0.01, -0.01]: Adam scales each step by the gradient's own size.
แนวทางการแก้
ลองทำเองก่อน แล้วค่อยเปิดคำใบ้ทีละข้อ
คำใบ้ 1
Track two moving averages per weight: one for the gradient direction and one for its squared size.
คำใบ้ 2
Apply bias correction using the current step number before dividing by the square root term.
คำใบ้ 3
Pay attention to epsilon in the denominator, because it prevents division by zero and changes the final update slightly.
ความซับซ้อนที่คาดหวัง
O(s × w) time, O(w) extra space
แหล่งอ้างอิง
โจทย์นี้ปรับให้เหมาะกับ CodeUtility กรุณาทำตามคำชี้แจงและข้อจำกัดด้านบน