As an example of the nonlinear Fokker-Planck equation, the mean field Langevin dynamics attracts attention due to its connection to (noisy) gradient descent on infinitely wide neural networks in the mean field regime, and hence the convergence property of the dynamics is of great theoretical interest. In this work, we give a simple and self-contained convergence rate analysis of the mean field Langevin dynamics with respect to the (regularized) objective function in both continuous and discrete time settings. The key ingredient of our proof is a proximal Gibbs distribution $p_q$ associated with the dynamics, which, in combination of techniques in [Vempala and Wibisono (2019)], allows us to develop a convergence theory parallel to classical results in convex optimization. Furthermore, we reveal that $p_q$ connects to the duality gap in the empirical risk minimization setting, which enables efficient empirical evaluation of the algorithm convergence.

This post deals with a recent optimizing method for training neural networks described in the paper Sharpness-Aware Minimization for Efficiently Improving Generalization by P. Foret et al. (December 2020). Honestly, the first time I read about the paper details, I really thought the procedure therein described (or something similar) had already been explored many years before by tons of people… I was even surprised to read that it worked in some contexts. Modern models train through optimization methods relying just on the training loss. These models can easily memorize the training data and are prone to overfitting. They have more parameters than needed and this large number of parameters provides no guarantee of proper generalization to the test set.

Expensive optimization problem (EOP) widely exists in various significant real-world applications. However, EOP requires expensive or even unaffordable costs for evaluating candidate solutions, which is expensive for the algorithm to find a satisfactory solution. Moreover, due to the fast-growing application demands in the economy and society, such as the emergence of the smart cities, the internet of things, and the big data era, solving EOP more efficiently has become increasingly essential in various fields, which poses great challenges on the problem-solving ability of optimization approach for EOP. Among various optimization approaches, evolutionary computation (EC) is a promising global optimization tool widely used for solving EOP efficiently in the past decades. Given the fruitful advancements of EC for EOP, it is essential to review these advancements in order to synthesize and give previous research experiences and references to aid the development of relevant research fields and real-world applications.

Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is yet to be shown whether AutoML techniques can effectively design online pipelines in dynamic environments. This study aims to automate pipeline design for online learning while continuously adapting to data drift. For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques. This system combines the inherent adaptation capabilities of online learners with the fast automated pipeline (re)optimization capabilities of AutoML. Focusing on optimization techniques that can adapt to evolving objectives, we evaluate asynchronous genetic programming and asynchronous successive halving to optimize these pipelines continually. We experiment on real and artificial data streams with varying types of concept drift to test the performance and adaptation capabilities of the proposed system. The results confirm the utility of OAML over popular online learning algorithms and underscore the benefits of continuous pipeline redesign in the presence of data drift.

Assistant Professor Wim van Rees and his team have developed simulations of self-propelled undulatory swimmers to better understand how fish-like deformable fins could improve propulsion in underwater devices, seen here in a top-down view. MIT ocean and mechanical engineers are using advances in scientific computing to address the ocean's many challenges, and seize its opportunities. There are few environments as unforgiving as the ocean. Its unpredictable weather patterns and limitations in terms of communications have left large swaths of the ocean unexplored and shrouded in mystery. "The ocean is a fascinating environment with a number of current challenges like microplastics, algae blooms, coral bleaching, and rising temperatures," says Wim van Rees, the ABS Career Development Professor at MIT. "At the same time, the ocean holds countless opportunities -- from aquaculture to energy harvesting and exploring the many ocean creatures we haven't discovered yet."

We consider the task of learning causal structures from data stored on multiple machines, and propose a novel structure learning method called distributed annealing on regularized likelihood score (DARLS) to solve this problem. We model causal structures by a directed acyclic graph that is parameterized with generalized linear models, so that our method is applicable to various types of data. To obtain a high-scoring causal graph, DARLS simulates an annealing process to search over the space of topological sorts, where the optimal graphical structure compatible with a sort is found by a distributed optimization method. This distributed optimization relies on multiple rounds of communication between local and central machines to estimate the optimal structure. We establish its convergence to a global optimizer of the overall score that is computed on all data across local machines. To the best of our knowledge, DARLS is the first distributed method for learning causal graphs with such theoretical guarantees. Through extensive simulation studies, DARLS has shown competing performance against existing methods on distributed data, and achieved comparable structure learning accuracy and test-data likelihood with competing methods applied to pooled data across all local machines. In a real-world application for modeling protein-DNA binding networks with distributed ChIP-Sequencing data, DARLS also exhibits higher predictive power than other methods, demonstrating a great advantage in estimating causal networks from distributed data.

The set-union knapsack problem (SUKP) is a constrained composed optimization problem. It is more difficulty for solving because values and weights depend on items and elements respectively. In this paper, we present two self-adjusting optimization algorithms for approximating SUKP from items and elements perspective respectively. By analyzing the dynamic characters in the SUKP, we design two types of self-adjusting repair and optimization operators that are based on the different loading process. We use the novel teaching-learning-based optimization algorithm (TLBO) to design a general discrete framework (DTLBO) suitable for these two types of operators. In addition, we introduce elite opposite search and natural selection mechanism into DTLBO to furtherly improve the performance of the algorithm from the perspective of population. Finally, we performed experimental comparisons on benchmark sets to verify the effectiveness of the proposed algorithm. The experimental results show that the item-based self-adjusting optimization algorithm I-DTLBO is outstanding, and the algorithm is superior to the other swarm intelligence methods for solving SUKP. IDTLBO algorithm reaches the upper boundary of the current swarm intelligence algorithms for solving SUKP in 10 instances, and gotten new upper boundary in 15 instances. The algorithm E-DTLBO based on element loading only perform slightly better on small and middle data sets, but worse on large-scale instances. It shows that element-based design is not suitable for solving SUKP.

There are few environments as unforgiving as the ocean. Its unpredictable weather patterns and limitations in terms of communications have left large swaths of the ocean unexplored and shrouded in mystery. "The ocean is a fascinating environment with a number of current challenges like microplastics, algae blooms, coral bleaching, and rising temperatures," says Wim van Rees, the ABS Career Development Professor at MIT. "At the same time, the ocean holds countless opportunities -- from aquaculture to energy harvesting and exploring the many ocean creatures we haven't discovered yet." Ocean engineers and mechanical engineers, like van Rees, are using advances in scientific computing to address the ocean's many challenges, and seize its opportunities. These researchers are developing technologies to better understand our oceans, and how both organisms and human-made vehicles can move within them, from the micro scale to the macro scale.

Internet of Vehicles (IoV) over Vehicular Ad-hoc Networks (VANETS) is an emerging technology enabling the development of smart cities applications for safer, efficient, and pleasant travel. These applications have stringent requirements expressed in Service Level Agreements (SLAs). Considering vehicles limited computational and storage capabilities, applications requests are offloaded into an integrated edge-cloud computing system. Existing offloading solutions focus on optimizing applications Quality of Service (QoS) while respecting a single SLA constraint. They do not consider the impact of overlapped requests processing. Very few contemplate the varying speed of a vehicle. This paper proposes a novel Artificial Intelligence (AI) QoS-SLA-aware genetic algorithm (GA) for multi-request offloading in a heterogeneous edge-cloud computing system, considering the impact of overlapping requests processing and dynamic vehicle speed. The objective of the optimization algorithm is to improve the applications' Quality of Service (QoS) by minimizing the total execution time. The proposed algorithm integrates an adaptive penalty function to assimilate the SLAs constraints in terms of latency, processing time, deadline, CPU, and memory requirements. Numerical experiments and comparative analysis are achieved between our proposed QoS-SLA-aware GA, random, and GA baseline approaches. The results show that the proposed algorithm executes the requests 1.22 times faster on average compared to the random approach with 59.9% less SLA violations. While the GA baseline approach increases the performance of the requests by 1.14 times, it has 19.8% more SLA violations than our approach.

Its goal is to provide a high quality implementation of classical optimization algorithms under a consistent API. This will create a copt directory. Now you can run the tests with py.test tests/