In convex optimization, relax and round / polishing is a procedure by which you perform a local search after coming up with a relaxation, and round into the actual feasible set (such as integers).

experiment design problem, but such that we ignore that \(m \lambda_{k}\) are integers.

Key Sequence

Notation

New Concepts

• minimum volume elipsolid
• centering
  • analytic center of inequalities
• classification
  • linear classification is convex
  • robust linear discrimination

Important Results / Claims

• relax and round

Questions

Interesting Factoids

• linear classification is convex

New Model

China would need to shift to new growth model… Since 1980, it relied on:

1. mobilization on two mechanisms
2. shift in control of resources to state to private

There may be thus diminishing returns.

a new growth model

• China’s capacity outstrips global demand
• incomes no longerr rising as rapidly
• foreign direct investment is slowing

Expansion of credit

China bank access accounts for a large percentage of global GDP; thus bad debt can accumulate and hurt. Banks is thus driving the infrastructure drive via credit. Credit growth comes up, GDP growdth comes down; bad state! Yet, almost 20% of enterprises are loosing money.

Supervised learning (also known as behavioral cloning) if the agent is learning what to do in an observe-act cycle) is a type of decision making method.

constituents

• input space: \(\mathcal{X}\)
• output space: \(\mathcal{Y}\)
• hypothesis/model/prediction: \(h : \mathcal{X} \to \mathcal{Y}\)

requirements

Our ultimate goal is to learn a good model \(h\) from the training set:

• what “good” means is hard to define
• we generally want to use the model on new data, not just the training set

continuous \(\mathcal{Y}\) is then called a regression problem; discrete \(\mathcal{Y}\) is called a classification problem.