2 citations · 3 across the 3 of their papers we have counts for
6 papers
Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee
Kohei Miyaguchi
We are concerned with the problem of hyperparameter selection for the fitted Q-evaluation (FQE). FQE is one of the state-of-the-art method for offline policy evaluation (OPE), whic…
Biases in In Silico Evaluation of Molecular Optimization Methods and Bias-Reduced Evaluation Methodology
Hiroshi Kajino, Kohei Miyaguchi, Takayuki Osogami
We are interested in in silico evaluation methodology for molecular optimization methods. Given a sample of molecules and their properties of our interest, we wish not only to trai…
PAC-Bayesian Transportation Bound
Kohei Miyaguchi
Empirically, the PAC-Bayesian analysis is known to produce tight risk bounds for practical machine learning algorithms. However, in its naive form, it can only deal with stochastic…
Adaptive Minimax Regret against Smooth Logarithmic Losses over High-Dimensional -Balls via Envelope Complexity
Kohei Miyaguchi, Kenji Yamanishi
We develop a new theoretical framework, the \emph{envelope complexity}, to analyze the minimax regret with logarithmic loss functions and derive a Bayesian predictor that adaptivel…
High-dimensional Penalty Selection via Minimum Description Length Principle
Kohei Miyaguchi, Kenji Yamanishi
We tackle the problem of penalty selection of regularization on the basis of the minimum description length (MDL) principle. In particular, we consider that the design space of the…
Normalized Maximum Likelihood with Luckiness for Multivariate Normal Distributions
Kohei Miyaguchi
The normalized maximum likelihood (NML) is one of the most important distribution in coding theory and statistics. NML is the unique solution (if exists) to the pointwise minimax r…