Global Concavity and Optimization in a Class of Dynamic Discrete Choice Models
Authors: Yiding Feng, Ekaterina Khmelnitskaya, Denis Nekipelov
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In particular, we demonstrate significant computational advantages in using a simple implementation policy gradient algorithm over existing nested fixed point algorithms used in Econometrics. [...] To demonstrate the performance of the algorithm, we use the data from Rust (1987) which made the standard benchmark for the Econometric analysis of MDPs. |
| Researcher Affiliation | Academia | 1Department of Computer Science, Northwestern University, Evanston, IL, USA 2Department of Economics, University of Virginia, Charlottesville, VA, USA. |
| Pseudocode | Yes | Algorithm 1 Lazy projection |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described. |
| Open Datasets | No | To demonstrate the performance of the algorithm, we use the data from Rust (1987) which made the standard benchmark for the Econometric analysis of MDPs. The paper cites Rust (1987) for the data source but does not provide a link, DOI, or repository for the dataset itself. |
| Dataset Splits | No | The paper discusses discretizing mileage and parameters for the transition process but does not specify any training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'RMSprop method' and 'ADAM' for optimization but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | We set the learning rate using the RMSprop method4. 4We use standard parameter values for RMSProp method: β = 0.1, ν = 0.001 and ϵ = 10 8. [...] The algorithm terminates at step k where the norm maxi |DVδ(k)(si)| τ for a given tolerance τ.5 The particular tolerance value used was 0.03 for illustrative purposes. |