Harel Lidar

Course summary · Feb 2025

Summary of Report

Mostly someone else’s words. I keep it as reading, not as my own writing.

A fundamental limitation of CBO approaches is that they all assume knowledge of the underlying casual graph. The typical problem formulation in BO is min⁡x∈Af(x)\min_{x \in \mathbb{A}} f(x) where A is the feasible set, x is an input sequence and f is a black box function. The two important aspects of the BO algorithm are:

  1. Bayesian statistical model: This is a surrogate model for the black-box function and is written as P(f(⋅))P(f(\cdot)), which is a probabilistic estimate for the true function f(⋅)f(\cdot)
  2. Acquisition function: This is the function that we are optimizing at each step of the BO algorithm and is written as α(⋅)\alpha(\cdot) This work assumes an underlying Gaussian Process. This modeling allows to quantify our current level of uncertainty regarding the graph and balance the exploration exploitation tradeoff. Further, by having a GP we essentially have a distribution over functions, hence by sampling new datapoints we can update our posterior and then also obtain a closed form formula for the current marginal likelihood of the variable of interest. In this report the acquisition functions that are used are either Expected Improvement - which aims to select the point with the highest improvement of the global optimum or Entropy Search - which aims to reduce uncertainty about the location of the global optimum by exploring
    regions of the search space that provide the most information.

Here we model our surrogate model using a GP, other methods of using BNNs our Neural Processes, which are made to deal with the computational intractability of GPs also exist. This work explores how to extend the GP framework to larger graphs by making use of the underlying causal model rather than just a black-box function optimization. The cold start problem, of having worthwhile questions at the early stages of exploration is a key theme in BO, here we try to make use of the causal model as well as observational data to solve this Could we perhaps encode “concpets”/“desiderata” etc?

TODOs