wovepaper — the arXiv observatory

NewEvery arXiv paper, its researchers & institutions — mapped.

papers

Publications (14)

Fairwashing: the risk of rationalization

Ulrich AÃ¯vodji, Hiromi Arai, Olivier Fortineau +3

Maximizing Invariant Data Perturbation with Stochastic Optimization

Kouichi Ikeno, Satoshi Hara

Finding Alternate Features in Lasso

Satoshi Hara, Takanori Maehara

Enumeration of Distinct Support Vectors for Interactive Decision Making

Kentaro Kanamori, Satoshi Hara, Masakazu Ishihata +1

Convex Hull Approximation of Nearly Optimal Lasso Solutions

Satoshi Hara, Takanori Maehara

Maximally Invariant Data Perturbation as Explanation

Satoshi Hara, Kouichi Ikeno, Tasuku Soma +1

Making Tree Ensembles Interpretable

Satoshi Hara, Kohei Hayashi

Anomaly detection in reconstructed quantum states using a machine-learning technique

Satoshi Hara, Takafumi Ono, Ryo Okamoto +2

Quantile regression approach to conditional mode estimation

Hirofumi Ota, Kengo Kato, Satoshi Hara

On Estimation of Conditional Modes Using Multiple Quantile Regressions

Hirofumi Ohta, Satoshi Hara

Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach

Satoshi Hara, Kohei Hayashi

Data Cleansing for Models Trained with SGD

Satoshi Hara, Atsushi Nitanda, Takanori Maehara

Consistent Nonparametric Different-Feature Selection via the Sparsest $k$-Subgraph Problem

Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa +4

Learning a Common Substructure of Multiple Graphical Gaussian Models

Satoshi Hara, Takashi Washio