Search Results for author:
Found 8 papers, 0 papers with code
Cumulative Stay-time Representation for Electronic Health Records in Medical Event Time Prediction
The MET of non-communicable diseases like diabetes is highly correlated to cumulative health conditions, more specifically, how much time the patient spent with specific health conditions in the past.
Biases in In Silico Evaluation of Molecular Optimization Methods and Bias-Reduced Evaluation Methodology
We are interested in in silico evaluation methodology for molecular optimization methods.
Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee
We are concerned with the problem of hyperparameter selection for the fitted Q-evaluation (FQE).
Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models
We consider the problem of offline policy evaluation~(OPE) with Markov decision processes~(MDPs), where the goal is to estimate the utility of given decision-making policies based on static datasets.
Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion
We are concerned with the problem of distributional prediction with incomplete features: The goal is to estimate the distribution of target variables given feature vectors with some of the elements missing.
PAC-Bayesian Transportation Bound
Empirically, the PAC-Bayesian analysis is known to produce tight risk bounds for practical machine learning algorithms.
Adaptive Minimax Regret against Smooth Logarithmic Losses over High-Dimensional $\ell_1$-Balls via Envelope Complexity
The resulting regret bound is so simple that it is completely determined with the smoothness of the loss function and the radius of the balls except with logarithmic factors, and it has a generalized form of existing regret/risk bounds.
High-dimensional Penalty Selection via Minimum Description Length Principle
In this situation, the luckiness-normalized-maximum-likelihood(LNML)-minimization approach is favorable, because LNML quantifies the goodness of regularized models with any forms of penalty functions in view of the minimum description length principle, and guides us to a good penalty function through the high-dimensional space.
