The no free lunch theorem states that no model is better suited to every problem. A question that arises from this is how to design methods that propose optimizers tailored to specific problems achieving state-of-the-art performance. This paper addresses this issue by proposing the use of meta-learning to infer population-based black-box optimizers that can automatically adapt to specific classes of problems. We suggest a general modeling of population-based algorithms that result in Learning-to-Optimize POMDP (LTO-POMDP), a meta-learning framework based on a specific partially observable Markov decision process (POMDP). From that framework's formulation, we propose to parameterize the algorithm using deep recurrent neural networks and use a meta-loss function based on stochastic algorithms' performance to train efficient data-driven optimizers over several related optimization tasks. The learned optimizers' performance based on this implementation is assessed on various black-box optimization tasks and hyperparameter tuning of machine learning models. Our results revealed that the meta-loss function encourages a learned algorithm to alter its search behavior so that it can easily fit into a new context. Thus, it allows better generalization and higher sample efficiency than state-of-the-art generic optimization algorithms, such as the Covariance matrix adaptation evolution strategy (CMA-ES).

In this paper, we develop two new algorithms, called, \textbf{FedDR} and \textbf{asyncFedDR}, for solving a fundamental nonconvex optimization problem in federated learning. Our algorithms rely on a novel combination between a nonconvex Douglas-Rachford splitting method, randomized block-coordinate strategies, and asynchronous implementation. Unlike recent methods in the literature, e.g., FedSplit and FedPD, our algorithms update only a subset of users at each communication round, and possibly in an asynchronous mode, making them more practical. These new algorithms also achieve communication efficiency and more importantly can handle statistical and system heterogeneity, which are the two main challenges in federated learning. Our convergence analysis shows that the new algorithms match the communication complexity lower bound up to a constant factor under standard assumptions. Our numerical experiments illustrate the advantages of the proposed methods compared to existing ones using both synthetic and real datasets.

Bayesian optimization has emerged as a powerful strategy to accelerate scientific discovery by means of autonomous experimentation. However, expensive measurements are required to accurately estimate materials properties, and can quickly become a hindrance to exhaustive materials discovery campaigns. Here, we introduce Gemini: a data-driven model capable of using inexpensive measurements as proxies for expensive measurements by correcting systematic biases between property evaluation methods. We recommend using Gemini for regression tasks with sparse data and in an autonomous workflow setting where its predictions of expensive to evaluate objectives can be used to construct a more informative acquisition function, thus reducing the number of expensive evaluations an optimizer needs to achieve desired target values. In a regression setting, we showcase the ability of our method to make accurate predictions of DFT calculated bandgaps of hybrid organic-inorganic perovskite materials. We further demonstrate the benefits that Gemini provides to autonomous workflows by augmenting the Bayesian optimizer Phoenics to yeild a scalable optimization framework leveraging multiple sources of measurement. Finally, we simulate an autonomous materials discovery platform for optimizing the activity of electrocatalysts for the oxygen evolution reaction. Realizing autonomous workflows with Gemini, we show that the number of measurements of a composition space comprising expensive and rare metals needed to achieve a target overpotential is significantly reduced when measurements from a proxy composition system with less expensive metals are available.

Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason could be the lack of guarantees on the performance of the intermediate executed policies, compared to an existing (already working) baseline policy. In this paper, we propose an online model-free algorithm that solves conservative exploration in the policy optimization problem. We show that the regret of the proposed approach is bounded by $\tilde{\mathcal{O}}(\sqrt{T})$ for both discrete and continuous parameter spaces.

It is important for a broad range of applications, including policy making [136], medical imaging [30], advertisement [22], the development of medical treatments [189], the evaluation of evidence within legal frameworks [183, 218], social science [82, 96, 246], biology [235], and many others. It is also a burgeoning topic in machine learning and artificial intelligence [17, 66, 76, 144, 210, 247, 255], where it has been argued that a consideration for causality is crucial for reasoning about the world. In order to discover causal relations, and thereby gain causal understanding, one may perform interventions and manipulations as part of a randomized experiment. These experiments may not only allow researchers or agents to identify causal relationships, but also to estimate the magnitude of these relationships. Unfortunately, in many cases, it may not be possible to undertake such experiments due to prohibitive cost, ethical concerns, or impracticality.

The performance of optimization algorithms relies crucially on their parameterizations. Finding good parameter settings is called algorithm tuning. The sequential parameter optimization (SPOT) package for R is a toolbox for tuning and understanding simulation and optimization algorithms. Model-based investigations are common approaches in simulation and optimization. Sequential parameter optimization has been developed, because there is a strong need for sound statistical analysis of simulation and optimization algorithms. SPOT includes methods for tuning based on classical regression and analysis of variance techniques; tree-based models such as CART and random forest; Gaussian process models (Kriging), and combinations of different meta-modeling approaches. Using a simple simulated annealing algorithm, we will demonstrate how optimization algorithms can be tuned using SPOT. The underling concepts of the SPOT approach are explained. This includes key techniques such as exploratory fitness landscape analysis and sensititvity analysis. Many examples illustrate how SPOT can be used for understanding the performance of algorithms and gaining insight into algorithm's behavior. Furthermore, we demonstrate how SPOT can be used as an optimizer and how a sophisticated ensemble approach is able to combine several meta models via stacking. This article exemplifies how SPOT can be used for automatic and interactive tuning.

Motivated by prior work connecting the geometry of the loss landscape and generalization, we introduce a novel, effective procedure for instead simulta- neously minimizing loss value and loss sharpness. In particular, our procedure, Sharpness-Aware Minimization (SAM), seeks parameters that lie in neighbor- hoods having uniformly low loss; this formulation results in a min-max optimiza- tion problem on which gradient descent can be performed efficiently. We present empirical results showing that SAM improves model generalization across a variety of benchmark datasets[1] In Deep Learning we use optimization algorithms such as SGD/Adam to achieve convergence in our model, which leads to finding the global minima, i.e a point where the loss of the training dataset is low. But several kinds of research such as Zhang et al have shown, many networks can easily memorize the training data and have the capacity to readily overfit, To prevent this problem and add more generalization, Researchers at Google have published a new paper called Sharpness Awareness Minimization which provides State of the Art results on CIFAR10 and other datasets. In this article, we will look at why SAM can achieve better generalization and how we can implement SAM in Pytorch.

Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an underground lava tube.

We introduce a stochastic version of the cutting-plane method for a large class of data-driven Mixed-Integer Nonlinear Optimization (MINLO) problems. We show that under very weak assumptions the stochastic algorithm is able to converge to an $\epsilon$-optimal solution with high probability. Numerical experiments on several problems show that stochastic cutting planes is able to deliver a multiple order-of-magnitude speedup compared to the standard cutting-plane method. We further experimentally explore the lower limits of sampling for stochastic cutting planes and show that for many problems, a sampling size of $O(\sqrt[3]{n})$ appears to be sufficient for high quality solutions.

Graph Convolutional Networks (GCNs) have achieved impressive empirical advancement across a wide variety of graph-related applications. Despite their great success, training GCNs on large graphs suffers from computational and memory issues. A potential path to circumvent these obstacles is sampling-based methods, where at each layer a subset of nodes is sampled. Although recent studies have empirically demonstrated the effectiveness of sampling-based methods, these works lack theoretical convergence guarantees under realistic settings and cannot fully leverage the information of evolving parameters during optimization. In this paper, we describe and analyze a general \textbf{\textit{doubly variance reduction}} schema that can accelerate any sampling method under the memory budget. The motivating impetus for the proposed schema is a careful analysis for the variance of sampling methods where it is shown that the induced variance can be decomposed into node embedding approximation variance (\emph{zeroth-order variance}) during forward propagation and layerwise-gradient variance (\emph{first-order variance}) during backward propagation. We theoretically analyze the convergence of the proposed schema and show that it enjoys an $\mathcal{O}(1/T)$ convergence rate. We complement our theoretical results by integrating the proposed schema in different sampling methods and applying them to different large real-world graphs. Code is public available at~\url{https://github.com/CongWeilin/SGCN.git}.