Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
OptStream: Releasing Time Series Privately
Authors: Ferdinando Fioretto, Pascal Van Hentenryck
JAIR 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | OPTSTREAM is evaluated on a test case involving the release of a real data stream from the largest European transmission operator. Experimental results show that OPTSTREAM may not only improve the accuracy of state-of-the-art methods by at least one order of magnitude but also supports accurate load forecasting on the privacy-preserving data. ... Section 6 performs a comprehensive experimental analysis of real data streams from energy load profiles. |
| Researcher Affiliation | Academia | Ferdinando Fioretto EMAIL School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA; Pascal Van Hentenryck EMAIL School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA |
| Pseudocode | Yes | Algorithm 1: SVT Sparse Vector Technique; Algorithm 2: OPTSTREAM data stream release; Algorithm 3: SAMPLE Adaptive L1-based sampler; Algorithm 4: POSTPROCESS Optimization-based post-processing |
| Open Source Code | No | The paper does not provide an explicit statement about the release of open-source code for the methodology described, nor does it include a link to a code repository. |
| Open Datasets | No | The source data was obtained through a collaboration with R eseau de Transport d Electricit e, the largest energy transmission system operator in Europe. ... The dataset contains the energy consumption for one year at a granularity of 30 minutes. ... The paper does not provide a direct link, DOI, or explicit statement of public availability for this specific dataset. |
| Dataset Splits | No | In our experiments, we use an ARMA model with parameters p q 1 to estimate the future 48 time steps (corresponding to a day) when trained with the past four weeks of the privacy-preserving data stream estimated using Laplace, DFT, and OPTSTREAM with L1-sampling. While a temporal splitting strategy is implied for forecasting, no explicit train/test/validation splits (e.g., percentages or specific counts for the overall dataset) are provided for the primary evaluation of OPTSTREAM. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as GPU models, CPU models, or memory specifications. |
| Software Dependencies | No | The paper mentions using an "Autoregressive Moving Average (ARMA) model" but does not specify the software or library used for its implementation, nor does it provide version numbers for any software dependencies. |
| Experiment Setup | Yes | The experiments set the number of Fourier coefficients in the DFT and sampling steps in OPTSTREAM to 10. The privacy loss allocated to perform each measurement is split equally. Additionally, for OPTSTREAM ϵs ϵp ϵo 1 3ϵ, and the L1-sampling procedure uses a threshold value θ of 1000 (which is about one tenth of the average load consumption in each region). ... We use an ARMA model with parameters p q 1 to estimate the future 48 time steps (corresponding to a day) when trained with the past four weeks... |