With the recent advance of representation learning algorithms on graphs (e.g., DeepWalk/GraphSage) and natural languages (e.g., Word2Vec/BERT) , the state-of-the art models can even achieve human-level performance over many downstream tasks, particularly for the task of node and sentence classification. However, most algorithms focus on large-scale models for static graphs and text corpus without considering the inherent dynamic characteristics or discovering the reasons behind the changes. This dissertation aims to efficiently model the dynamics in graphs (such as social networks and citation graphs) and understand the changes in texts (specifically news titles and personal biographies). To achieve this goal, we utilize the renowned Personalized PageRank algorithm to create effective dynamic network embeddings for evolving graphs. Our proposed approaches significantly improve the running time and accuracy for both detecting network abnormal intruders and discovering entity meaning shifts over large-scale dynamic graphs. For text changes, we analyze the post-publication changes in news titles to understand the intents behind the edits and discuss the potential impact of titles changes from information integrity perspective. Moreover, we investigate self-presented occupational identities in Twitter users' biographies over five years, investigating job prestige and demographics effects in how people disclose jobs, quantifying over-represented jobs and their transitions over time.

Natural terrain complexity often necessitates agile movements like jumping in animals to improve traversal efficiency. To enable similar capabilities in quadruped robots, complex real-time jumping maneuvers are required. Current research does not adequately address the problem of online omnidirectional jumping and neglects the robot's kinodynamic constraints during trajectory generation. This paper proposes a general and complete cascade online optimization framework for omnidirectional jumping for quadruped robots. Our solution systematically encompasses jumping trajectory generation, a trajectory tracking controller, and a landing controller. It also incorporates environmental perception to navigate obstacles that standard locomotion cannot bypass, such as jumping from high platforms. We introduce a novel jumping plane to parameterize omnidirectional jumping motion and formulate a tightly coupled optimization problem accounting for the kinodynamic constraints, simultaneously optimizing CoM trajectory, Ground Reaction Forces (GRFs), and joint states. To meet the online requirements, we propose an accelerated evolutionary algorithm as the trajectory optimizer to address the complexity of kinodynamic constraints. To ensure stability and accuracy in environmental perception post-landing, we introduce a coarse-to-fine relocalization method that combines global Branch and Bound (BnB) search with Maximum a Posteriori (MAP) estimation for precise positioning during navigation and jumping. The proposed framework achieves jump trajectory generation in approximately 0.1 seconds with a warm start and has been successfully validated on two quadruped robots on uneven terrains. Additionally, we extend the framework's versatility to humanoid robots.

As a key task in machine learning, data classification is essentially to find a suitable coordinate system to represent data features of different classes of samples. This paper proposes the mutual-energy inner product optimization method for constructing a feature coordinate system. First, by analyzing the solution space and eigenfunctions of partial differential equations describing a non-uniform membrane, the mutual-energy inner product is defined. Second, by expressing the mutual-energy inner product as a series of eigenfunctions, it shows a significant advantage of enhancing low-frequency features and suppressing high-frequency noise, compared with the Euclidean inner product. And then, a mutual-energy inner product optimization model is built to extract data features, and convexity and concavity properties of its objective function are discussed. Next, by combining the finite element method, a stable and efficient sequential linearization algorithm is constructed to solve the optimization model. This algorithm only solves equations including positive definite symmetric matrix and linear programming with a few constraints, and its vectorized implementation is discussed. Finally, the mutual-energy inner product optimization method is used to construct feature coordinates, and multi-class Gaussian classifiers are trained on the MINST training set. Good prediction results of Gaussian classifiers are achieved on the MINST test set.

Model-based control is a crucial component of robotic navigation. However, it often struggles with entrapment in local minima due to its inherent nature as a finite, myopic optimization procedure. Previous studies have addressed this issue but sacrificed either solution quality due to their reactive nature or computational efficiency in generating explicit paths for proactive guidance. To this end, we propose a motion planning method that proactively avoids local minima without any guidance from global paths. The key idea is repulsive potential augmentation, integrating high-level directional information into the Model Predictive Path Integral control as a single repulsive term through an artificial potential field. We evaluate our method through theoretical analysis and simulations in environments with obstacles that induce local minima. Results show that our method guarantees the avoidance of local minima and outperforms existing methods in terms of global optimality without decreasing computational efficiency.

Although adaptive optimization algorithms have been successful in many applications, there are still some mysteries in terms of convergence analysis that have not been unraveled. This paper provides a novel non-convex analysis of adaptive optimization to uncover some of these mysteries. Our contributions are three-fold. First, we show that an increasing or large enough momentum parameter for the first-order moment used in practice is sufficient to ensure the convergence of adaptive algorithms whose adaptive scaling factors of the step size are bounded. Second, our analysis gives insights for practical implementations, e.g., increasing the momentum parameter in a stage-wise manner in accordance with stagewise decreasing step size would help improve the convergence. Third, the modular nature of our analysis allows its extension to solving other optimization problems, e.g., compositional, min-max and bilevel problems. As an interesting yet non-trivial use case, we present algorithms for solving non-convex min-max optimization and bilevel optimization that do not require using large batches of data to estimate gradients or double loops as the literature do. Our empirical studies corroborate our theoretical results.

This paper aims to make a mark in the future of sustainable robotics, where efficient algorithms are required to carry out tasks like environmental monitoring and precision agriculture efficiently. We proposed a hybrid algorithm that combines Artificial Bee Colony (ABC) with Levy flight to optimize adaptive sensor placement alongside an important notion of hotspots from domain knowledge experts. By enhancing exploration and exploitation, our approach significantly improves the identification of critical hotspots. This algorithm also finds its usecases for broader search and rescue operations applications, demonstrating its potential in optimization problems across various domains.

The main challenge of multimodal optimization problems is identifying multiple peaks with high accuracy in multidimensional search spaces with irregular landscapes. This work proposes the Multiple Global Peaks Big Bang-Big Crunch (MGP-BBBC) algorithm, which addresses the challenge of multimodal optimization problems by introducing a specialized mechanism for each operator. The algorithm expands the Big Bang-Big Crunch algorithm, a state-of-the-art metaheuristic inspired by the universe's evolution. Specifically, MGP-BBBC groups the best individuals of the population into cluster-based centers of mass and then expands them with a progressively lower disturbance to guarantee convergence. During this process, it (i) applies a distance-based filtering to remove unnecessary elites such that the ones on smaller peaks are not lost, (ii) promotes isolated individuals based on their niche count after clustering, and (iii) balances exploration and exploitation during offspring generation to target specific accuracy levels. Experimental results on twenty multimodal benchmark test functions show that MGP-BBBC generally performs better or competitively with respect to other state-of-the-art multimodal optimizers.

The exponential growth in data availability in recent years has led to new formulations of data-driven optimization problems. One such formulation is that of stochastic optimization problems with contextual information, where the goal is to optimize the expected value of a certain function given some contextual information (also called features) that accompany the main data of interest. The contextual information then allows for a better estimation of the quantity of interest via machine learning methods, thereby leading to better solutions. Oftentimes, however, machine learning methods yield just a pointwise estimate instead of an entire distribution. In this paper we show that, when the problem to be solved is a class of two-stage stochastic programs (namely, those with fixed recourse matrix and fixed costs), under mild assumptions the problem can be solved with just one scenario. While such a scenario - which does not have be unique - is usually unknown, we present an integrated learning and optimization procedure that yields the best approximation of that scenario within the modeler's pre-specified set of parameterized forecast functions. Numerical results conducted with inventory problems from the literature (with synthetic data) as well as a bike-sharing problem with real data demonstrate that the proposed approach performs well when compared to benchmark methods from the literature.

Latent Bayesian optimization (LBO) approaches have successfully adopted Bayesian optimization over a continuous latent space by employing an encoder-decoder architecture to address the challenge of optimization in a high dimensional or discrete input space. LBO learns a surrogate model to approximate the black-box objective function in the latent space. However, we observed that most LBO methods suffer from the `misalignment problem`, which is induced by the reconstruction error of the encoder-decoder architecture. It hinders learning an accurate surrogate model and generating high-quality solutions. In addition, several trust region-based LBO methods select the anchor, the center of the trust region, based solely on the objective function value without considering the trust region`s potential to enhance the optimization process. To address these issues, we propose Inversion-based Latent Bayesian Optimization (InvBO), a plug-and-play module for LBO. InvBO consists of two components: an inversion method and a potential-aware trust region anchor selection. The inversion method searches the latent code that completely reconstructs the given target data. The potential-aware trust region anchor selection considers the potential capability of the trust region for better local optimization. Experimental results demonstrate the effectiveness of InvBO on nine real-world benchmarks, such as molecule design and arithmetic expression fitting tasks. Code is available at https://github.com/mlvlab/InvBO.

Language model performance depends on identifying the optimal mixture of data groups to train on (e.g., law, code, math). Prior work has proposed a diverse set of methods to efficiently learn mixture proportions, ranging from fitting regression models over training runs to dynamically updating proportions throughout training. Surprisingly, we find that no existing method consistently outperforms a simple stratified sampling baseline in terms of average test perplexity per group. In this paper, we study the cause of this inconsistency by unifying existing methods into a standard optimization framework. We show that all methods set proportions to minimize total loss, subject to a method-specific mixing law -- an assumption on how loss is a function of mixture proportions. We find that existing parameterizations of mixing laws can express the true loss-proportion relationship empirically, but the methods themselves often set the mixing law parameters inaccurately, resulting in poor and inconsistent performance. Finally, we leverage the insights from our framework to derive a new online method named Aioli, which directly estimates the mixing law parameters throughout training and uses them to dynamically adjust proportions. Empirically, Aioli outperforms stratified sampling on 6 out of 6 datasets by an average of 0.28 test perplexity points, whereas existing methods fail to consistently beat stratified sampling, doing up to 6.9 points worse. Moreover, in a practical setting where proportions are learned on shorter runs due to computational constraints, Aioli can dynamically adjust these proportions over the full training run, consistently improving performance over existing methods by up to 12.01 test perplexity points.