x

LESSWRONG
LW

Gradient Descent — LessWrong

You are viewing version 1.0.0 of this page. Click here to view the latest version.

Gradient Descent

Edited by Ruby last updated 8th Sep 2021

You are viewing revision 1.0.0, last edited by Ruby

stub

Add Posts

Posts tagged Gradient Descent

7

46Hypothesis: gradient descent prefers general circuits

4y

26

6

36Why Aligning an LLM is Hard, and How to Make it Easier

1y

3

6

35The Best Way to Align an LLM: Is Inner Alignment Now a Solved Problem?

8mo

34

2

102Pretraining on Aligned AI Data Dramatically Reduces Misalignment—Even After Post-Training

20d

12

2

64A "Bitter Lesson" Approach to Aligning AGI and ASI

2y

41

2

56Gradient descent is not just more efficient genetic algorithms

4y

14

2

42Why Reality Has A Well-Known Math Bias

7mo

20

2

40Visual Exploration of Gradient Descent (many images)

5mo

9

1

72Conditions for mathematical equivalence of Stochastic Gradient Descent and Natural Selection

4y

19

1

30We Need To Know About Continual Learning

3y

14

1

5The Human's Role in Mesa Optimization

2y

0

Add Posts