Conditional Probability Estimation

An online journal club on the topics Conditional Probability Estimation. Our cover topics on all sorts of probabilistic approach, such as VAE, normalizing, graph neural network, probabilistic time series forecasting.

Introduction: Conditional Probability Estimation

References for Probability Estimation Club

Published:
Summary: A list of references for our online discussions.
Pages: 60

Inferring causal impact using Bayesian structural time-series models

Published:
Summary: Our topic for this session is Inferring causal impact using Bayesian structural time-series models (arXiv:1506.00356). Abstract Abstract of Inferring causal impact using Bayesian structural time-series models (arXiv:1506.00356): An important problem in econometrics and marketing is to infer the causal impact that a designed market intervention has exerted on an outcome metric over time. This paper proposes to infer causal impact on the basis of a diffusion-regression state-space model that predicts the counterfactual market response in a synthetic control that would have occurred had no intervention taken place.
Pages: 60

58 Diffusion Models for Time Series: Workshop

Published:
Summary: Workshop: Let code the model together. Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

57 Diffusion Models for Time Series: Review the Model

Published:
Summary: Topics: Review the model Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

56 Diffusion Models for Time Series: Dataloader Discussions and Next Steps

Published:
Summary: Topics: 我们上周几个人写了一个 dataloader ，大概实现了 从 pandas dataframe -> pytorch dataloader apply transformations, e.g., moving slicing to produce fixed length input+output 这周我们来讨论一下这个写法，然后讨论一下接下来如何分工。 Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

55 Diffusion Models for Time Series: Dataloader and Collation

Published:
Summary: Topics: dataloader construction Input pandas dataframe and output batched, transformed tensors Necessary transformations including fixed length input and moving-slicing. Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

54 Diffusion Models for Time Series: Dataloader

Published:
Summary: Topics: dataloader construction Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

53 Diffusion Models for Time Series: Data

Published:
Summary: Topics: data explorations, dataloader construction https://github.com/orgs/neuronstar/projects/2/views/2?pane=issue&itemId=21411846 https://github.com/orgs/neuronstar/projects/2/views/2?pane=issue&itemId=19112919 Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

52 Diffusion Models for Time Series: Initiation

Published:
Summary: Discuss how to proceed: Data format, PyTorch Lightning. Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

51 Diffusion Models for Time Series: the Paper

Published:
Summary: Let’s discuss the idea behind the project. Rasul K, Seward C, Schuster I, Vollgraf R. Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting. arXiv [cs.LG]. 2021. Available: http://arxiv.org/abs/2101.12072. Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

50 Diffusion Models for Time Series: Session 1

Published:
Summary: Get ready to write our own version of diffusion model for time series forecasting. https://github.com/neuronstar/ts-diffusion Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60

49 GitHub Actions for Data Scientists

Published:
Summary: Automate tasks using GitHub Actions: Test code Build docs Scrape data from websites Build LaTeX resume Demos here: https://github.com/emptymalei/github-actions-for-data-scientists Use the following timezone tool or click on the “Add to Calendar” button on the sidebar. Click here for an interactive widget.
Pages: 60