← Back to KHAO

GitHub ·

The usual approach to this problem is to sample many possible inputs, run them all through the model

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

◌ Single Source

wide_random_mlps_mse_vs_flops.png.

Paper: Estimating the expected output of wide random MLPs more efficiently than sampling Code: mlp_cumulant_propagation GitHub repo.

Key facts

Summary

This post covers joint work with Wilson Wu, George Robinson, Mike Winer, Victor Lecomte and Paul Christiano. In ARC's latest paper, they study the following problem: given a randomly initialized multilayer perceptron (MLP), produce an estimate for the expected output of the model under Gaussian input. The team are excited about this result as an early step towards their goal of producing mechanistic estimates that outperform random sampling for any trained neural network. In their paper, they consider MLPs with weights, defined by where the activation function is applied coordinatewise, and is taken to be by default. An estimation algorithm takes in and a tolerance parameter, and aims to estimate to within an error of around.

Read full article at Alignment Forum →

#GitHub