3.6k citations
- Japan Science and Technology AgencyJP16 papers
- RIKENJP15 papers
- The University of TokyoJP15 papers
- VTT Technical Research Centre of FinlandFI6 papers
- Tohoku UniversityJP5 papers
- Massachusetts Institute of TechnologyUS4 papers
- MIT Lincoln LaboratoryUS4 papers
- National Institute of Advanced Industrial Science and TechnologyJP4 papers
- NEC (United States)US4 papers
- RIKEN Advanced Science InstituteJP4 papers
- RIKEN Center for Emergent Matter ScienceJP4 papers
- University of California, Santa BarbaraUS4 papers
6 papers · 1 filter
Regularization of Field-Aware Factorization Machine through Ising Model
Yasuharu Okamoto
We examined the use of the Ising model as an regularization method for field-aware factorization machines (FFM). This approach improves generalization performance and has the…
Efficient Learning of Discrete-Continuous Computation Graphs
David Friede, Mathias Niepert
Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are…
Best-of-Both-Worlds Algorithms for Partial Monitoring
Taira Tsuchiya, Shinji Ito, Junya Honda
This study considers the partial monitoring problem with -actions and -outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded bot…
What is Next when Sequential Prediction Meets Implicitly Hard Interaction?
Kaixi Hu, Lin Li, Qing Xie +2
Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most…
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
Mathias Niepert, Pasquale Minervini, Luca Franceschi
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propo…
An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation
Makoto Takamoto, Yusuke Morishita, Hitoshi Imaoka
Compressing deep neural network (DNN) models becomes a very important and necessary technique for real-world applications, such as deploying those models on mobile devices. Knowled…