Accelerated Sampling with Stacked Restricted Boltzmann Machines
Authors: Jorge Fernandez-de-Cossio-Diaz, Clément Roussel, Simona Cocco, Remi Monasson
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We illustrate the efficiency of the Stacked Tempering method with respect to standard and replica exchange MC on several datasets: MNIST, in-silico Lattice Proteins, and the 2D-Ising model. |
| Researcher Affiliation | Academia | Laboratory of Physics of the Ecole Normale Supérieure. CNRS UMR 8023 & PSL Research, Sorbonne Université. 24 rue Lhomond, 75005 Paris, France. |
| Pseudocode | No | The paper describes the Stacked Tempering procedure in text and with diagrams (Figure 2), but it does not provide any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include any explicit statement about releasing source code or provide a link to a code repository. |
| Open Datasets | Yes | MNIST. is a large dataset of 28 28 pixel images of handwritten digits (Le Cun, 1998)... Lattice Proteins (LP). ... Shakhnovich & Gutin (1990) and Mirny & Shakhnovich (2001)... 2D Ising model. ... Onsager (1944). |
| Dataset Splits | No | The paper uses datasets like MNIST, Lattice Proteins, and 2D Ising model for training and evaluating sampling efficiency, but it does not specify explicit training/validation/test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments (e.g., GPU/CPU models, memory specifications, or cloud computing instances). |
| Software Dependencies | No | The paper describes the algorithms and models used (RBMs, AGS, PT) but does not list any specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | ST with a stack of four RBMs (N1 = 784, M1 = N2 = 200, M2 = N3 = 100, M3 = N4 = 25, M4 = 10)... Three RBMs are used (N1 = 27 20 as amino acids can take 20 possible values, M1 = N2 = 800, M2 = N3 = 50, M3 = 25)... A stack of 3 RBMs is used in ST, with 50, 20 and 1 hidden unit. |