Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMulti-Level Evolution Strategies for High-Resolution Black-Box Control
72
0
0.0
(
0
)
Added by
Ofer Shir
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper introduces a multi-level (m-lev) mechanism into Evolution Strategies (ESs) in order to address a class of global optimization problems that could benefit from fine discretization of their decision variables. Such problems arise in engineering and scientific applications, which possess a multi-resolution control nature, and thus may be formulated either by means of low-resolution variants (providing coarser approximations with presumably lower accuracy for the general problem) or by high-resolution controls. A particular scientific application concerns practical Quantum Control (QC) problems, whose targeted optimal controls may be discretized to increasingly higher resolution, which in turn carries the potential to obtain better control yields. However, state-of-the-art derivative-free optimization heuristics for high-resolution formulations nominally call for an impractically large number of objective function calls. Therefore, an effective algorithmic treatment for such problems is needed. We introduce a framework with an automated scheme to facilitate guided-search over increasingly finer levels of control resolution for the optimization problem, whose on-the-fly learned parameters require careful adaptation. We instantiate the proposed m-lev self-adaptive ES framework by two specific strategies, namely the classical elitist single-child (1+1)-ES and the non-elitist multi-child derandomized $(mu_W,lambda)$-sep-CMA-ES. We first show that the approach is suitable by simulation-based optimization of QC systems which were heretofore viewed as too complex to address. We also present a laboratory proof-of-concept for the proposed approach on a basic experimental QC system objective.
rate research
Read More
The encoding of solutions in black-box optimization is a delicate, handcrafted balance between expressiveness and domain knowledge -- between exploring a wide variety of solutions, and ensuring that those solutions are useful. Our main insight is that this process can be automated by generating a dataset of high-performing solutions with a quality diversity algorithm (here, MAP-Elites), then learning a representation with a generative model (here, a Variational Autoencoder) from that dataset. Our second insight is that this representation can be used to scale quality diversity optimization to higher dimensions -- but only if we carefully mix solutions generated with the learned representation and those generated with traditional variation operators. We demonstrate these capabilities by learning an low-dimensional encoding for the inverse kinematics of a thousand joint planar arm. The results show that learned representations make it possible to solve high-dimensional problems with orders of magnitude fewer evaluations than the standard MAP-Elites, and that, once solved, the produced encoding can be used for rapid optimization of novel, but similar, tasks. The presented techniques not only scale up quality diversity algorithms to high dimensions, but show that black-box optimization encodings can be automatically learned, rather than hand designed.
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the optimal strategy for membership inference with a few assumptions on the distribution of the parameters. We show that optimal attacks only depend on the loss function, and thus black-box attacks are as good as white-box attacks. As the optimal strategy is not tractable, we provide approximations of it leading to several inference methods, and show that existing membership inference methods are coarser approximations of this optimal strategy. Our membership attacks outperform the state of the art in various settings, ranging from a simple logistic regression to more complex architectures and datasets, such as ResNet-101 and Imagenet.
Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the Evolution Strategies gradient and the gradient of a similar class of algorithms, Finite Differences (FD).(Zhang et al. 2017, Lehman et al. 2018) Several investigations into the subject have been performed, investigating the formal motivational differences(Lehman et al. 2018) between ES and FD, as well as the differences in a standard benchmark problem in Machine Learning, the MNIST classification problem(Zhang et al. 2017). This paper proves that while the gradients are different, they converge as the dimension of the vector under optimization increases.
In recent decades, with the emergence of numerous novel intelligent optimization algorithms, many optimization researchers have begun to look for a basic search mechanism for their schemes that provides a more essential explanation of their studies. This paper aims to study the basic mechanism of an algorithm for black-box optimization with quantum theory. To achieve this goal, the Schroedinger equation is employed to establish the relationship between the optimization problem and the quantum system, which makes it possible to study the dynamic search behaviors in the evolution process with quantum theory. Moreover, to explore the basic behavior of the optimization system, the optimization problem is assumed to be decomposed and approximated. Then, a multilevel approximation quantum dynamics model of the optimization algorithm is established, which provides a mathematical and physical framework for the analysis of the optimization algorithm. Correspondingly, the basic search behavior based on this model is derived, which is governed by quantum theory. Comparison experiments and analysis between different bare-bones algorithms confirm the existence of the quantum mechanic based basic search mechanism of the algorithm on black-box optimization.
We consider the problem of controlling an unknown linear time-invariant dynamical system from a single chain of black-box interactions, with no access to resets or offline simulation. Under the assumption that the system is controllable, we give the first efficient algorithm that is capable of attaining sublinear regret in a single trajectory under the setting of online nonstochastic control. This resolves an open problem on the stochastic LQR problem, and in a more challenging setting that allows for adversarial perturbations and adversarially chosen and changing convex loss functions. We give finite-time regret bounds for our algorithm on the order of $2^{tilde{O}(mathcal{L})} + tilde{O}(text{poly}(mathcal{L}) T^{2/3})$ for general nonstochastic control, and $2^{tilde{O}(mathcal{L})} + tilde{O}(text{poly}(mathcal{L}) sqrt{T})$ for black-box LQR, where $mathcal{L}$ is the system size which is an upper bound on the dimension. The crucial step is a new system identification method that is robust to adversarial noise, but incurs exponential cost. To complete the picture, we investigate the complexity of the online black-box control problem, and give a matching lower bound of $2^{Omega(mathcal{L})}$ on the regret, showing that the additional exponential cost is inevitable. This lower bound holds even in the noiseless setting, and applies to any, randomized or deterministic, black-box control method.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
