Search Results for author:
Found 17 papers, 1 papers with code
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
Over the past decade, a large number of white-box adversarial robustness evaluation methods (i. e., attacks) have been proposed, ranging from single-step to multi-step methods and from individual to ensemble methods.
Theoretical Advantage of Multiobjective Evolutionary Algorithms for Problems with Different Degrees of Conflict
We prove that for any set of weights, the set of optima found by scalarization approach cannot cover the full Pareto front.
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications.
A Crowding Distance That Provably Solves the Difficulties of the NSGA-II in Many-Objective Optimization
These results suggest that our truthful version of the NSGA-II has the same good performance as the classic NSGA-II in two objectives, but can resolve the drastic problems in more than two objectives.
Runtime Analysis of the SMS-EMOA for Many-Objective Optimization
To this aim, we first propose a many-objective counterpart, the m-objective mOJZJ, of the bi-objective OJZJ, which is the first many-objective multimodal benchmark for runtime analysis.
Theoretical Analyses of Evolutionary Algorithms on Time-Linkage OneMax with General Weights
We prove that except for some small and positive time-linkage effects (that is, for weights $0$ and $1$), randomized local search (RLS) and (1+1)EA cannot converge to the global optimum with a positive probability.
Runtime Analysis for the NSGA-II: Proving, Quantifying, and Explaining the Inefficiency For Many Objectives
The NSGA-II is one of the most prominent algorithms to solve multi-objective optimization problems.
From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms
Building on a recent quantitative analysis of how the population size leads to genetic drift, we design a smart-restart mechanism for EDAs.
Approximation Guarantees for the Non-Dominated Sorting Genetic Algorithm II (NSGA-II)
In this work, we study how well it approximates the Pareto front when the population size is smaller.
Mathematical Runtime Analysis for the Non-Dominated Sorting Genetic Algorithm II (NSGA-II)
The non-dominated sorting genetic algorithm II (NSGA-II) is the most intensively used multi-objective evolutionary algorithm (MOEA) in real-world applications.
Choosing the Right Algorithm With Hints From Complexity Theory
Our finding that the unary unbiased black-box complexity is only $O(n^2)$ suggests the Metropolis algorithm as an interesting candidate and we prove that it solves the DLB problem in quadratic time.
When Non-Elitism Meets Time-Linkage Problems
However, only two elitist algorithms (1+1)EA and ($\mu$+1)EA are analyzed, and it is unknown whether the non-elitism mechanism could help to escape the local optima existed in OneMax$_{(0, 1^n)}$.
Theoretical Analyses of Multiobjective Evolutionary Algorithms on Multimodal Objectives
As a first step towards a deeper understanding of how evolutionary algorithms solve multimodal multiobjective problems, we propose the OJZJ problem, a bi-objective problem composed of two objectives isomorphic to the classic jump function benchmark.
Analysis of Evolutionary Algorithms on Fitness Function with Time-linkage Property
In real-world applications, many optimization problems have the time-linkage property, that is, the objective function value relies on the current solution as well as the historical solutions.
From Understanding Genetic Drift to a Smart-Restart Parameter-less Compact Genetic Algorithm
One of the key difficulties in using estimation-of-distribution algorithms is choosing the population size(s) appropriately: Too small values lead to genetic drift, which can cause enormous difficulties.
Sharp Bounds for Genetic Drift in Estimation of Distribution Algorithms
This paper further proves that for PBIL with parameters $\mu$, $\lambda$, and $\rho$, in an expected number of $\Theta(\mu/\rho^2)$ iterations the sampling frequency of a neutral bit leaves the interval $[\Theta(\rho/\mu), 1-\Theta(\rho/\mu)]$ and then always the same value is sampled for this bit, that is, the frequency approaches the corresponding boundary value with maximum speed.
Working Principles of Binary Differential Evolution
On the technical side, we observe that the strong stochastic dependencies in the random experiment describing a run of BDE prevent us from proving all desired results with the mathematical rigor that was successfully used in the analysis of other evolutionary algorithms.
