AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Neural Methods for Point-wise Dependency Estimation

Yao-Hung Hubert Tsai, Han Zhao, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov

NeurIPS 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Mutual information estimation · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Probabilistic Classifier instead of Density-Ratio Fitting for point-wise dependency estimationAudio-to-text retrieval · Audio-to-text 1:5 matching, test splittop-1 retrieval accuracy: 96.24% vs 92.26%Improved
Use Density-Ratio Fitting Coding instead of CPC or Probabilistic Classifier CodingSelf-supervised representation learning · Shallow and deep visual representation learningdownstream linear-evaluation performanceImproved
Use Probabilistic Classifier Coding instead of CPCSelf-supervised representation learning · Shallow CIFAR10downstream linear-evaluation performanceImproved
Use Probabilistic Classifier Coding instead of CPCSelf-supervised representation learning · Other reported self-supervised experimentsdownstream linear-evaluation performanceHurt
Estimate MI by plugging in Probabilistic Classifier or Density-Ratio Fitting estimates rather than using most neural lower-bound estimatorsMI estimation · Correlated Gaussian and Cubic tasksbias and varianceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy