187 citations · 252 across the 10 of their papers we have counts for
10 papers
Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages
Yingjie Hu, Gengchen Mai, Chris Cundy +6
Social media messages posted by people during natural disasters often contain important location descriptions, such as the locations of victims. Recent research has shown that many…
Concrete Score Matching: Generalized Score Matching for Discrete Data
Chenlin Meng, Kristy Choi, Jiaming Song +1
Representing probability distributions by the gradient of their density functions has proven effective in modeling a wide range of continuous data modalities. However, this represe…
LMPriors: Pre-Trained Language Models as Task-Specific Priors
Kristy Choi, Chris Cundy, Sanjari Srivastava +1
Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encour…
ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Chenlin Meng, Linqi Zhou, Kristy Choi +2
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key r…
Density Ratio Estimation via Infinitesimal Classification
Kristy Choi, Chenlin Meng, Yang Song +1
Density ratio estimation (DRE) is a fundamental machine learning technique for comparing two probability distributions. However, existing methods struggle in high-dimensional setti…
Featurized Density Ratio Estimation
Kristy Choi, Madeline Liao, Stefano Ermon
Density ratio estimation serves as an important technique in the unsupervised machine learning toolbox. However, such ratios are difficult to estimate for complex, high-dimensional…
Neural Network Compression for Noisy Storage Devices
Berivan Isik, Kristy Choi, Xin Zheng +4
Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices. Despite the significant progress in NN mo…
Fair Generative Modeling via Weak Supervision
Kristy Choi, Aditya Grover, Trisha Singh +2
Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating b…
Meta-Amortized Variational Inference and Learning
Mike Wu, Kristy Choi, Noah Goodman +1
Despite the recent success in probabilistic modeling and their applications, generative models trained using traditional inference techniques struggle to adapt to new distributions…
Neural Joint Source-Channel Coding
Kristy Choi, Kedar Tatwawadi, Aditya Grover +2
For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and chan…