Search Results for author:
Found 39 papers, 13 papers with code
Probabilistic Model-Based Dynamic Architecture Search
The experimental results show that the proposed architecture search method is fast and can achieve comparable performance to the existing methods.
Probabilistic Prediction of Ship Maneuvering Motion using Ensemble Learning with Feedforward Neural Networks
In the field of Maritime Autonomous Surface Ships (MASS), the accurate modeling of ship maneuvering motion for harbor maneuvers is a crucial technology.
Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm
We term this specific algorithm the categorical compact genetic algorithm (ccGA).
Stepwise Alignment for Constrained Language Model Policy Optimization
This paper formulates human value alignment as an optimization problem of the language model policy to maximize reward under a safety constraint, and then proposes an algorithm, Stepwise Alignment for Constrained Policy Optimization (SACPO).
CMA-ES with Learning Rate Adaptation
The results show that the CMA-ES with the proposed learning rate adaptation works well for multimodal and/or noisy problems without extremely expensive learning rate tuning.
Theoretical Analysis of Explicit Averaging and Novel Sign Averaging in Comparison-Based Search
Explicit averaging takes the sample average of noisy objective function values and is widely used as a simple and versatile noise-handling technique.
Verbosity Bias in Preference Labeling by Large Language Models
In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning.
Data Augmentation Methods of Dynamic Model Identification for Harbor Maneuvers using Feedforward Neural Network
In this paper, we improve the generalization performance of the dynamic model for the automatic berthing and unberthing controller by introducing data augmentation.
Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems.
CMA-ES with Learning Rate Adaptation: Can CMA-ES with Default Population Size Solve Multimodal and Noisy Problems?
The results demonstrate that, when the proposed learning rate adaptation is used, the CMA-ES with default population size works well on multimodal and/or noisy problems, without the need for extremely expensive learning rate tuning.
Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min--Max Optimization and its Application to Berthing Control Tasks
In this study, we consider a continuous min--max optimization problem $\min_{x \in \mathbb{X} \max_{y \in \mathbb{Y}}}f(x, y)$ whose objective function is a black-box.
Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents.
Collision probability reduction method for tracking control in automatic docking / berthing using reinforcement learning
This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles.
Adaptive Scenario Subset Selection for Worst-Case Optimization and its Application to Well Placement Optimization
To reduce the number of simulations required and increase the number of restarts for better local optimum solutions, we propose a new approach referred to as adaptive scenario subset selection (AS3).
Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification
In this study, we focus on scenarios involving a simulation environment with uncertainty parameters and the set of their possible values, called the uncertainty parameter set.
Convergence rate of the (1+1)-evolution strategy on locally strongly convex functions with lipschitz continuous gradient and their monotonic transformations
Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization.
CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
Therefore, we propose a loss function that can improve the separation of the important class by setting the margin only for the important class, called Class-sensitive Additive Angular Margin Loss (CAMRI Loss).
Black-Box Min--Max Continuous Optimization Using CMA-ES with Worst-case Ranking Approximation
(I) As the influence of the interaction term between $x$ and $y$ (e. g., $x^\mathrm{T} B y$) on the Lipschitz smooth and strongly convex-concave function $f$ increases, the approaches converge to an optimal solution at a slower rate.
Monotone Improvement of Information-Geometric Optimization Algorithms with a Surrogate Function
We assume that the surrogate function is maintained so that the population version of the Kendall's rank correlation coefficient between the surrogate function and the objective function under the candidate sampling distribution is greater than or equal to a predefined threshold.
A Two-phase Framework with a Bézier Simplex-based Interpolation Method for Computationally Expensive Multi-objective Optimization
The first phase in TPB aims to approximate a few Pareto optimal solutions by optimizing a sequence of single-objective scalar problems.
On Neural Network Identification for Low-Speed Ship Maneuvering Model
A new system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests is proposed in this study.
System Parameter Exploration of Ship Maneuvering Model for Automatic Docking / Berthing using CMA-ES
The main contributions of this study are as follows: (i) construct the system-based mathematical model on berthing by optimizing system parameters with a reduced amount of model tests than the CMT-based scheme; (ii) Find the favorable choice of objective function and type of training data for optimization.
Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
The challenge is that we have to discover in an unsupervised manner a set of concepts, i. e., A, B and C, that is useful for the explaining the classifier.
Saddle Point Optimization with Approximate Minimization Oracle and its Application to Robust Berthing Control
We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately.
Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution
When ML techniques are applied to game domains with non-tile-based level representation, such as Angry Birds, where objects in a level are specified by real-valued parameters, ML often fails to generate playable levels.
Saddle Point Optimization with Approximate Minimization Oracle
Our approach locates approximate solutions $x'$ and $y'$ to $\min_{x'}f(x', y)$ and $\max_{y'}f(x, y')$ at a given point $(x, y)$ and updates $(x, y)$ toward these approximate solutions $(x', y')$ with a learning rate $\eta$.
Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions
The convergence rate, that is, the decrease rate of the distance from a search point $m_t$ to the optimal solution $x^*$, is proven to be in $O(\exp( - L / \mathrm{Tr}(H) ))$, where $L$ is the smallest eigenvalue of $H$ and $\mathrm{Tr}(H)$ is the trace of $H$.
Warm Starting CMA-ES for Hyperparameter Optimization
Hyperparameter optimization (HPO), formulated as black-box optimization (BBO), is recognized as essential for automation and high performance of machine learning approaches.
AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment
In this paper, we propose a novel search strategy for one-shot and sparse propagation NAS, namely AdvantageNAS, which further reduces the time complexity of NAS by reducing the number of search iterations.
Generate (non-software) Bugs to Fool Classifiers
We first show the feasibility of this approach in an attack against an image classifier by employing generative adversarial networks that produce image patches that have the appearance of a natural object to fool the target model.
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
It accepts arbitrary search space (widely-applicable) and enables to employ a gradient-based simultaneous optimization of weights and architecture (fast).
Diagonal Acceleration for Covariance Matrix Adaptation Evolution Strategies
In numerical experiments with dd-CMA-ES up to dimension 5120, we observe remarkable improvements over the original covariance matrix adaptation on functions with coordinate-wise ill-conditioning.
Adaptive Ranking Based Constraint Handling for Explicitly Constrained Black-Box Optimization
The proposed technique is aimed at solving explicitly constrained black-box continuous optimization problems, in which the explicit constraint is a constraint whereby the computational time for the constraint violation and its (numerical) gradient are negligible compared to that for the objective function.
Unauthorized AI cannot Recognize Me: Reversible Adversarial Example
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.
Parameterless Stochastic Natural Gradient Method for Discrete Optimization and its Application to Hyper-Parameter Optimization for Neural Network
This paper proposes a parameterless BBDO algorithm based on information geometric optimization, a recent framework for black box optimization using stochastic natural gradient.
Sample Reuse via Importance Sampling in Information Geometric Optimization
The experimental results show that the sample reuse helps to reduce the number of function evaluations on many benchmark functions for both the PBIL and the pure rank-$\mu$ update CMA-ES.
Drift Theory in Continuous Search Spaces: Expected Hitting Time of the (1+1)-ES with 1/5 Success Rule
This paper explores the use of the standard approach for proving runtime bounds in discrete domains---often referred to as drift analysis---in the context of optimization on a continuous domain.
Dynamic Optimization of Neural Network Structures Using Probabilistic Modeling
We consider a probability distribution that generates network structures, and optimize the parameters of the distribution instead of directly optimizing the network structure.
Analysis of a Natural Gradient Algorithm on Monotonic Convex-Quadratic-Composite Functions
In this paper we investigate the convergence properties of a variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES).
