1.4k citations · 4.2k across the 41 of their papers we have counts for
7 papers · 1 filter
Stochastic Submodular Maximization: The Case of Coverage Functions
Mohammad Reza Karimi, Mario Lucic, Hamed Hassani +1
Stochastic optimization of continuous objectives is at the heart of modern machine learning. However, many important problems are of discrete nature and often involve submodular ob…
Are GANs Created Equal? A Large-Scale Study
Mario Lucic, Karol Kurach, Marcin Michalski +2
Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is stil…
One-Shot Coresets: The Case of k-Clustering
Olivier Bachem, Mario Lucic, Silvio Lattanzi
Scaling clustering algorithms to massive data sets is a challenging task. Recently, several successful approaches based on data summarization methods, such as coresets and sketches…
Training Gaussian Mixture Models at Scale via Coresets
Mario Lucic, Matthew Faulkner, Andreas Krause +1
How can we train a statistical mixture model on a massive data set? In this work we show how to construct coresets for mixtures of Gaussians. A coreset is a weighted subset of the…
Practical Coreset Constructions for Machine Learning
Olivier Bachem, Mario Lucic, Andreas Krause
We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. W…
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
Olivier Bachem, Mario Lucic, S. Hamed Hassani +1
Uniform deviation bounds limit the difference between a model's expected loss and its loss on an empirical sample uniformly for all models in a learning problem. As such, they are…