Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Choice Computation - Correlated Utilities

No description

Karthik Natarajan

on 16 June 2015

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Choice Computation - Correlated Utilities

A Convex Optimization Approach for Computing Correlated Choice Probabilities with Many Alternatives

Choice Probability
Cross Moment Model
New Results
Computational Results

Closed form, numerical integration or simulation

Convex optimization formulation
Random utility maximization

Representative agent model

i.i.d. Gumbel random error term

Entropy maximization
Random utility maximization

Representative agent model
Random utility maximization

Representative agent model
Multivariate normal random error terms with
zero mean and given covariance matrix

Several simulation based methods

No simple form that is amenable for computation

Multinomial Logit & Probit Models
Distribution that maximizes the expected agent utility given first two moments:

Previous works shows that this reduces to solving a semidefinite program (SDP):
Choice probability in CMM
A representative agent model for CMM:

Efficiently computable gradient that makes a simple gradient ascent method suitable for CMM:
Selin Damla Ahipasaoglu (SUTD), Xiaobo Li (University of Minnesota), Karthik Natarajan (SUTD)
Full transcript