Weakly Supervised Label Learning Flows

1 code implementation • 19 Feb 2023 • You Lu, Chidubem Arachie, Bert Huang

In this paper, we develop label learning flows (LLF), a general framework for weakly supervised learning problems.

Weakly-supervised Learning

Woodbury Transformations for Deep Generative Flows

1 code implementation • NeurIPS 2020 • You Lu, Bert Huang

In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via Sylvester's determinant identity.

Normalising Flows

Structured Output Learning with Conditional Generative Flows

2 code implementations • 30 May 2019 • You Lu, Bert Huang

Traditional structured prediction models try to learn the conditional likelihood, i. e., p(y|x), to capture the relationship between the structured output y and the input features x.

Structured Prediction Variational Inference

Block Belief Propagation for Parameter Learning in Markov Random Fields

no code implementations • 9 Nov 2018 • You Lu, Zhiyuan Liu, Bert Huang

Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient.

Why ADAGRAD Fails for Online Topic Modeling

no code implementations • EMNLP 2017 • You Lu, Jeffrey Lund, Jordan Boyd-Graber

For online topic modeling, the magnitude of gradients is very large.

Topic Models Variational Inference