activity
20122026
most citedScore-Based Generative Modeling through Stochastic Differential Equations

1.3k citations · 2.3k across the 91 of their papers we have counts for

collaborators
Showing 2018Show all

24 papers · 1 filter

stat.ML2018

Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization

Aditya Grover, Stefano Ermon

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertain…

cs.LG2018

Learning Controllable Fair Representations

Jiaming Song, Pratyusha Kalluri, Aditya Grover +2

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility o…

cs.LG2018

Bias and Generalization in Deep Generative Models: An Empirical Study

Shengjia Zhao, Hongyu Ren, Arianna Yuan +3

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models i…

cs.LG2018

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…

cs.LG2018

Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference

Mike Wu, Noah Goodman, Stefano Ermon

Stochastic optimization techniques are standard in variational inference algorithms. These methods estimate gradients by approximating expectations with independent Monte Carlo sam…

cs.CV2018

Learning to Interpret Satellite Images Using Wikipedia

Evan Sheehan, Burak Uzkent, Chenlin Meng +4

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitat…