6 papers · 1 filter
Pure exploration in multi-armed bandits with low rank structure using oblivious sampler
Yaxiong Liu, Atsuyoshi Nakamura, Kohei Hatano +1
In this paper, we consider the low rank structure of the reward sequence of the pure exploration problems. Firstly, we propose the separated setting in pure exploration problem, wh…
Boosting-based Construction of BDDs for Linear Threshold Functions and Its Application to Verification of Neural Networks
Yiping Tang, Kohei Hatano, Eiji Takimoto
Understanding the characteristics of neural networks is important but difficult due to their complex structures and behaviors. Some previous work proposes to transform neural netwo…
Boosting as Frank-Wolfe
Ryotaro Mitsuboshi, Kohei Hatano, Eiji Takimoto
Some boosting algorithms, such as LPBoost, ERLPBoost, and C-ERLPBoost, aim to solve the soft margin optimization problem with the -norm regularization. LPBoost rapidly conv…
Theory and Algorithms for Shapelet-based Multiple-Instance Learning
Daiki Suehiro, Kohei Hatano, Eiji Takimoto +3
We propose a new formulation of Multiple-Instance Learning (MIL), in which a unit of data consists of a set of instances called a bag. The goal is to find a good classifier of bags…
Multiple-Instance Learning by Boosting Infinitely Many Shapelet-based Classifiers
Daiki Suehiro, Kohei Hatano, Eiji Takimoto +3
We propose a new formulation of Multiple-Instance Learning (MIL). In typical MIL settings, a unit of data is given as a set of instances called a bag and the goal is to find a good…
Boosting the kernelized shapelets: Theory and algorithms for local features
Daiki Suehiro, Kohei Hatano, Eiji Takimoto +3
We consider binary classification problems using local features of objects. One of motivating applications is time-series classification, where features reflecting some local close…