activity
20172020
most citedA Method to Model Conditional Distributions with Normalizing Flows

5 citations · 8 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG20203 cited

Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy

Zhisheng Xiao, Qing Yan, Yali Amit

In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the la…

cs.LG20195 cited

A Method to Model Conditional Distributions with Normalizing Flows

Zhisheng Xiao, Qing Yan, Yali Amit

In this work, we investigate the use of normalizing flows to model conditional distributions. In particular, we use our proposed method to analyze inverse problems with invertible…

cs.CV2019

Generative Latent Flow

Zhisheng Xiao, Qing Yan, Yali Amit

In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representati…

cs.NE2018

Deep learning with asymmetric connections and Hebbian updates

Yali Amit

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic…

stat.ML2017

Deformable Classifiers

Jiajun Shen, Yali Amit

Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transform…

stat.ML2017

Dynamic Partition Models

Marc Goessling, Yali Amit

We present a new approach for learning compact and intuitive distributed representations with binary encoding. Rather than summing up expert votes as in products of experts, we emp…