M
Mario Lucic
Researcher at Google
Publications - 80
Citations - 6420
Mario Lucic is an academic researcher from Google. The author has contributed to research in topics: Cluster analysis & Unsupervised learning. The author has an hindex of 34, co-authored 80 publications receiving 4765 citations. Previous affiliations of Mario Lucic include ETH Zurich & IBM.
Papers
More filters
Proceedings Article
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Francesco Locatello,Stefan Bauer,Mario Lucic,Gunnar Rätsch,Sylvain Gelly,Bernhard Schölkopf,Olivier Bachem +6 more
TL;DR: The authors show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data, and suggest that future work on disentanglement learning should be explicit about the role of inductive bias and (implicit) supervision.
Proceedings Article
Are GANs Created Equal? A Large-Scale Study
TL;DR: This paper conducted a large-scale empirical study on state-of-the-art GAN models and evaluation measures and found that most models can reach similar scores with enough hyperparameter optimization and random restarts, and that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes.
Posted Content
Are GANs Created Equal? A Large-Scale Study
TL;DR: This article conducted a large-scale empirical study on state-of-the-art GAN models and evaluation measures and found that most models can reach similar scores with enough hyperparameter optimization and random restarts, and that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes.
Posted Content
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour,Katherine Heller,Dan Moldovan,Ben Adlam,Babak Alipanahi,Alex Beutel,Christina Chen,Jonathan Deaton,Jacob Eisenstein,Matthew D. Hoffman,Farhad Hormozdiari,Neil Houlsby,Shaobo Hou,Ghassen Jerfel,Alan Karthikesalingam,Mario Lucic,Yi-An Ma,Cory Y. McLean,Diana Mincu,Akinori Mitani,Andrea Montanari,Zachary Nado,Vivek T. Natarajan,Christopher Nielson,Thomas F. Osborne,Rajiv Raman,Kim Ramasamy,Rory Sayres,Jessica Schrouff,Martin G. Seneviratne,Shannon Sequeira,Harini Suresh,Victor Veitch,Max Vladymyrov,Xuezhi Wang,Kellie Webster,Steve Yadlowsky,Taedong Yun,Xiaohua Zhai,D. Sculley +39 more
TL;DR: This work shows the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain, and shows that this problem appears in a wide variety of practical ML pipelines.
Posted Content
Recent Advances in Autoencoder-Based Representation Learning
TL;DR: An in-depth review of recent advances in representation learning with a focus on autoencoder-based models and makes use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features.