Mario Lucic

is this you? claim profile

∙ 0 followers
Google ∙ ETH Zurich

Research Scientist in the Google Brain team

Underspecification Presents Challenges for Credibility in Modern Machine Learning

ML models often exhibit unexpectedly poor behavior when they are deploye...
11/06/2020 ∙ by Alexander D'Amour, et al. ∙ 30 ∙ share

read it
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation

The idea behind the unsupervised learning of disentangled representation...
10/27/2020 ∙ by Francesco Locatello, et al. ∙ 27 ∙ share

read it
Which Model to Transfer? Finding the Needle in the Growing Haystack

Transfer learning has been recently popularized as a data-efficient alte...
10/13/2020 ∙ by Cèdric Renggli, et al. ∙ 19 ∙ share

read it
Representation learning from videos in-the-wild: An object-centric approach

We propose a method to learn image representations from uncurated videos...
10/06/2020 ∙ by Rob Romijnders, et al. ∙ 6 ∙ share

read it
A Commentary on the Unsupervised Learning of Disentangled Representations

The goal of the unsupervised learning of disentangled representations is...
07/28/2020 ∙ by Francesco Locatello, et al. ∙ 15 ∙ share

read it
On Robustness and Transferability of Convolutional Neural Networks

Modern deep convolutional networks (CNNs) are often criticized for not g...
07/16/2020 ∙ by Josip Djolonga, et al. ∙ 15 ∙ share

read it
Self-Supervised Learning of Video-Induced Visual Invariances

We propose a general framework for self-supervised learning of transfera...
12/05/2019 ∙ by Michael Tschannen, et al. ∙ 14 ∙ share

read it
Semantic Bottleneck Scene Generation

Coupling the high-fidelity generation capabilities of label-conditional ...
11/26/2019 ∙ by Samaneh Azadi, et al. ∙ 33 ∙ share

read it
On Mutual Information Maximization for Representation Learning

Many recent methods for unsupervised or self-supervised representation l...
07/31/2019 ∙ by Michael Tschannen, et al. ∙ 0 ∙ share

read it
Evaluating Generative Models Using Divergence Frontiers

Despite the tremendous progress in the estimation of generative models, ...
05/26/2019 ∙ by Josip Djolonga, et al. ∙ 0 ∙ share

read it
High-Fidelity Image Generation With Fewer Labels

Deep generative models are becoming a cornerstone of modern machine lear...
03/06/2019 ∙ by Mario Lucic, et al. ∙ 14 ∙ share

read it
Recent Advances in Autoencoder-Based Representation Learning

Learning useful representations with little or no supervision is a key c...
12/12/2018 ∙ by Michael Tschannen, et al. ∙ 0 ∙ share

read it
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

In recent years, the interest in unsupervised learning of disentangled r...
11/29/2018 ∙ by Francesco Locatello, et al. ∙ 4 ∙ share

read it
Self-Supervised Generative Adversarial Networks

Conditional GANs are at the forefront of natural image synthesis. The ma...
11/27/2018 ∙ by Ting Chen, et al. ∙ 0 ∙ share

read it
On Self Modulation for Generative Adversarial Networks

Training Generative Adversarial Networks (GANs) is notoriously challengi...
10/02/2018 ∙ by Ting Chen, et al. ∙ 0 ∙ share

read it
The GAN Landscape: Losses, Architectures, Regularization, and Normalization

Generative Adversarial Networks (GANs) are a class of deep generative mo...
07/12/2018 ∙ by Karol Kurach, et al. ∙ 6 ∙ share

read it
Assessing Generative Models via Precision and Recall

Recent advances in generative modeling have led to an increased interest...
05/31/2018 ∙ by Mehdi S. M. Sajjadi, et al. ∙ 0 ∙ share

read it
Deep Generative Models for Distribution-Preserving Lossy Compression

We propose and study the problem of distribution-preserving lossy compre...
05/28/2018 ∙ by Michael Tschannen, et al. ∙ 2 ∙ share

read it
Are GANs Created Equal? A Large-Scale Study

Generative adversarial networks (GAN) are a powerful subclass of generat...
11/28/2017 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it
One-Shot Coresets: The Case of k-Clustering

Scaling clustering algorithms to massive data sets is a challenging task...
11/27/2017 ∙ by Olivier Bachem, et al. ∙ 0 ∙ share

read it
Stochastic Submodular Maximization: The Case of Coverage Functions

Stochastic optimization of continuous objectives is at the heart of mode...
11/05/2017 ∙ by Mohammad Reza Karimi, et al. ∙ 0 ∙ share

read it
Training Mixture Models at Scale via Coresets

How can we train a statistical mixture model on a massive data set? In t...
03/23/2017 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it
Practical Coreset Constructions for Machine Learning

We investigate coresets - succinct, small summaries of large data sets -...
03/19/2017 ∙ by Olivier Bachem, et al. ∙ 0 ∙ share

read it
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means

Uniform deviation bounds limit the difference between a model's expected...
02/27/2017 ∙ by Olivier Bachem, et al. ∙ 0 ∙ share

read it
Scalable and Distributed Clustering via Lightweight Coresets

Coresets are compact representations of data sets such that models train...
02/27/2017 ∙ by Olivier Bachem, et al. ∙ 0 ∙ share

read it
Horizontally Scalable Submodular Maximization

A variety of large-scale machine learning problems can be cast as instan...
05/31/2016 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it
Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning

Faced with massive data, is it possible to trade off (statistical) risk,...
05/02/2016 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it
Linear-time Outlier Detection via Sensitivity

Outliers are ubiquitous in modern data sets. Distance-based techniques a...
05/02/2016 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it
Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures

Coresets are efficient representations of data sets such that models tra...
08/21/2015 ∙ by Mario Lucic, et al. ∙ 0 ∙ share

read it

Mario Lucic

Featured Co-authors