253 citations
- Technicolor (Germany)DE18 papers
- Technicolor (France)FR11 papers
- Stanford UniversityUS7 papers
- Adobe Systems (United States)US6 papers
- Massachusetts Institute of TechnologyUS5 papers
- Rutgers, The State University of New JerseyUS4 papers
- University of MichiganUS4 papers
- Max Planck Institute for InformaticsDE3 papers
- University of AlbertaCA3 papers
- University of Wisconsin–MadisonUS3 papers
- Yahoo (United States)US3 papers
- Centre Inria de l'Université de LilleFR2 papers
15 papers · 1 filter
Learning from a single labeled face and a stream of unlabeled data
Branislav Kveton, Michal Valko
Face recognition from a single image per person is a challenging problem because the training sample is extremely small. We consider a variation of this problem. In our problem, we…
Conditional anomaly detection with soft harmonic functions
Michal Valko, Branislav Kveton, Hamed Valizadegan +2
In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response or a class label. We develop a new non-paramet…
Matrix Completion in the Unit Hypercube via Structured Matrix Factorization
Emanuele Bugliarello, Swayambhoo Jain, Vineeth Rakesh
Several complex tasks that arise in organizations can be simplified by mapping them into a matrix completion problem. In this paper, we address a key challenge faced by our company…
Wide Compression: Tensor Ring Nets
Wenqi Wang, Yifan Sun, Brian Eriksson +2
Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications. In order to obtain performance gains, these networks have grown larger…
Combinatorial Cascading Bandits
Branislav Kveton, Zheng Wen, Azin Ashkan +1
We propose combinatorial cascading bandits, a class of partial monitoring problems where at each step a learning agent chooses a tuple of ground items subject to constraints and re…
Cascading Bandits: Learning to Rank in the Cascade Model
Branislav Kveton, Csaba Szepesvari, Zheng Wen +1
A search engine usually outputs a list of web pages. The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user…