9 citations · 50 across the 30 of their papers we have counts for
30 papers
Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off
Maaya Sakata, Kazuto Fukuchi
Post-hoc controllability of fair machine learning models, the ability to control the trade-off between fairness and accuracy after training, is valuable for practical deployment. E…
Provable Data Scaling Law for Meta Learning via Complexity Minimization
Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui
Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-tra…
Provable Target Sample Complexity Improvements as Pre-Trained Models Scale
Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui
Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted…
Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
Kazuto Fukuchi
We address the regression problem under the constraint of demographic parity, a commonly used fairness definition. Recent studies have revealed fair minimax optimal regression algo…
Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
Shojiro Yamabe, Kazuto Fukuchi, Jun Sakuma
This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired…
Adversarial Attacks on Hidden Tasks in Multi-Task Learning
Yu Zhe, Rei Nagaike, Daiki Nishiyama +2
Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective w…
Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
Mitsuhiro Fujikawa, Yohei Akimoto, Jun Sakuma +1
Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution, demonstrating significant benefits in various applications. T…
Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto +1
A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-b…
Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min--Max Optimization and its Application to Berthing Control Tasks
Atsuhiro Miyagi, Yoshiki Miyauchi, Atsuo Maki +3
In this study, we consider a continuous min--max optimization problem whose objective function is a black-box. We propose a…
Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
Rei Sato, Kazuto Fukuchi, Jun Sakuma +1
We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments…
Adaptive Scenario Subset Selection for Worst-Case Optimization and its Application to Well Placement Optimization
Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma +1
In this study, we consider simulation-based worst-case optimization problems with continuous design variables and a finite scenario set. To reduce the number of simulations require…
Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification
Takumi Tanabe, Rei Sato, Kazuto Fukuchi +2
In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to…
CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
Daiki Nishiyama, Kazuto Fukuchi, Youhei Akimoto +1
In real-world applications of multi-class classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (…
Convergence rate of the (1+1)-evolution strategy on locally strongly convex functions with lipschitz continuous gradient
Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma +1
Evolution strategy (ES) is one of the promising classes of algorithms for black-box continuous optimization. Despite its broad successes in applications, theoretical analysis on th…
Demographic Parity Constrained Minimax Optimal Regression under Linear Model
Kazuto Fukuchi, Jun Sakuma
We explore the minimax optimal error associated with a demographic parity-constrained regression problem within the context of a linear model. Our proposed model encompasses a broa…
Black-Box Min--Max Continuous Optimization Using CMA-ES with Worst-case Ranking Approximation
Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma +1
In this study, we investigate the problem of min-max continuous optimization in a black-box setting . A popular approach updates and simultaneously…
Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto +1
We aim to explain a black-box classifier with the form: `data X is classified as class Y because X \textit{has} A, B and \textit{does not have} C' in which A, B, and C are high-lev…
Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution
Takumi Tanabe, Kazuto Fukuchi, Jun Sakuma +1
Video game level generation based on machine learning (ML), in particular, deep generative models, has attracted attention as a technique to automate level generation. However, app…
Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions
Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma +1
The (1+1)-evolution strategy (ES) with success-based step-size adaptation is analyzed on a general convex quadratic function and its monotone transformation, that is, $f(x) = g((x…
Statistically Significant Pattern Mining with Ordinal Utility
Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto +1
Statistically significant patterns mining (SSPM) is an essential and challenging data mining task in the field of knowledge discovery in databases (KDD), in which each pattern is e…
Locally Differentially Private Minimum Finding
Kazuto Fukuchi, Chia-Mu Yu, Arashi Haishima +1
We investigate a problem of finding the minimum, in which each user has a real value and we want to estimate the minimum of these values under the local differential privacy constr…
Faking Fairness via Stealthily Biased Sampling
Kazuto Fukuchi, Satoshi Hara, Takanori Maehara
Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to rai…
Minimax Optimal Additive Functional Estimation with Discrete Distribution
Kazuto Fukuchi, Jun Sakuma
This paper addresses a problem of estimating an additive functional given i.i.d. samples drawn from a discrete distribution with alphabet size . The additi…
Unauthorized AI cannot Recognize Me: Reversible Adversarial Example
Jiayang Liu, Weiming Zhang, Kazuto Fukuchi +2
In this study, we propose a new methodology to control how user's data is recognized and used by AI via exploiting the properties of adversarial examples. For this purpose, we prop…