Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Self-Supervised Inference in State-Space Models
Authors: David Ruhe, Patrick ForrΓ©
ICLR 2022 | Venue PDF | LLM Run Details | Input Tokens: 23,143 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,178 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform three experiments. (1) A linear dynamics filtering experiment, where we show how our models approximate the optimal solution with sufficient data. We also report that including expert knowledge can yield better estimates of latent states. (2) A more challenging chaotic Lorenz smoothing experiment that shows how our models perform on par with recently proposed supervised models. (3) An audio denoising experiment that uses real-world noise showing practical applicability of the methods. |
| Researcher Affiliation | Academia | David Ruhe AI4Science, AMLab, Anton Pannekoek Institute University of Amsterdam, The Netherlands EMAIL Patrick Forr e AI4Science, AMLab University of Amsterdam, The Netherlands EMAIL |
| Pseudocode | Yes | E ALGORITHMS Algorithm 1: Recursive Filter (Inference) input : Data (time-series) y0:K = (y0, . . . , y K), emission matrices H and R, parameters Ο. output: ... |
| Open Source Code | No | We are in the process of releasing code for the current work. |
| Open Datasets | Yes | Specifically, we use the Speech Commands spoken audio dataset (Warden, 2018). |
| Dataset Splits | Yes | We simulate a K := 131, 072 trajectory for training, K := 16, 384 trajectory for validation and K := 32, 768 for testing. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments. It mentions neural networks but no underlying hardware. |
| Software Dependencies | No | The paper mentions software components like 'Gated Recurrent Unit (GRU) network' and 'neural networks' but does not provide specific version numbers for any libraries, frameworks (e.g., PyTorch, TensorFlow), or programming languages used. |
| Experiment Setup | Yes | F EXPERIMENTS: DETAILS... We used c = 0.06, Ο = 0.17, t := 1 and covariance ... H := 1 0 0 0 0 0 0 0 0 1 0 0 R := 0.52 1 0 0 1. We integrate the system using dt = 0.00001 and sample it uniformly at t = 0.05. We use Ο = 28, Ο = 10, Ξ² = 8/3. ... We use R := 0.52I. |