128 citations
- The University of TokyoJP20 papers
- Department of Physics, Mathematics and InformaticsBY6 papers
- Japan Science and Technology AgencyJP5 papers
- Department of Mathematical SciencesRU4 papers
- The University of OsakaJP3 papers
- Kobe UniversityJP2 papers
- Ochanomizu UniversityJP2 papers
- RIKENJP2 papers
- Sophia UniversityJP2 papers
- Tokyo Institute of TechnologyJP2 papers
- Advanced Institute of Industrial TechnologyJP1 paper
- Atacama Large Millimeter Submillimeter ArrayCL1 paper
4 papers · 1 filter
An inexact infeasible arc-search interior-point method for linear optimization problems
Einosuke Iida, Makoto Yamashita
We propose an inexact infeasible arc-search interior-point method for solving linear optimization problems. The method combines an arc-search strategy with inexact solutions to New…
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation
Tomoya Murata, Taiji Suzuki
We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a…
On -hyperparameter Learning via Bilevel Nonsmooth Optimization
Takayuki Okuno, Akiko Takeda, Akihiro Kawana +1
We propose a bilevel optimization strategy for selecting the best hyperparameter value for the nonsmooth regularizer with . The concerned bilevel optimization pr…
A compact representation for minimizers of -submodular functions
Hiroshi Hirai, Taihei Oki
A -submodular function is a generalization of submodular and bisubmodular functions. This paper establishes a compact representation for minimizers of a -submodular function…