activity
20152021
most citedLossy Image Compression with Compressive Autoencoders

259 citations · 424 across the 5 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML2020

Universally Quantized Neural Compression

Eirikur Agustsson, Lucas Theis

A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization. We demon…

stat.ML2019

Discriminative Topic Modeling with Logistic LDA

Iryna Korshunova, Hanchen Xiong, Mateusz Fedoryszak +1

Despite many years of research into latent Dirichlet allocation (LDA), applying LDA to collections of non-categorical items is still challenging. Yet many problems with much richer…

stat.ML2019

Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction

Sofia Ira Ktena, Alykhan Tejani, Lucas Theis +5

One of the challenges in display advertising is that the distribution of features and click through rate (CTR) can exhibit large shifts over time due to seasonality, changes to ad…

stat.ML2017259 cited

Lossy Image Compression with Compressive Autoencoders

Lucas Theis, Wenzhe Shi, Andrew Cunningham +1

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements an…

stat.ML201512 cited

A trust-region method for stochastic variational inference with applications to streaming data

Lucas Theis, Matthew D. Hoffman

Stochastic variational inference allows for fast posterior inference in complex Bayesian models. However, the algorithm is prone to local optima which can make the quality of the p…

stat.ML20159 cited

Supervised learning sets benchmark for robust spike detection from calcium imaging signals

Lucas Theis, Philipp Berens, Emmanouil Froudarakis +6

A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces. We systematically evaluate a range…