Control system optimization has long been a fundamental challenge in robotics. While recent advancements have led to the development of control algorithms that leverage learning-based approaches, such as SafeOpt, to optimize single feedback controllers, scaling these methods to high-dimensional complex systems with multiple controllers remains an open problem. In this paper, we propose a novel learning-based control optimization method, which enhances the additive Gaussian process-based Safe Bayesian Optimization algorithm to efficiently tackle high-dimensional problems through kernel selection. We use PID controller optimization in drones as a representative example and test the method on Safe Control Gym, a benchmark designed for evaluating safe control techniques. We show that the proposed method provides a more efficient and optimal solution for high-dimensional control optimization problems, demonstrating significant improvements over existing techniques.

Many applications require minimizing a family of optimization problems indexed by some hyperparameter $\lambda \in \Lambda$ to obtain an entire solution path. Traditional approaches proceed by discretizing $\Lambda$ and solving a series of optimization problems. We propose an alternative approach that parameterizes the solution path with a set of basis functions and solves a \emph{single} stochastic optimization problem to learn the entire solution path. Our method offers substantial complexity improvements over discretization. When using constant-step size SGD, the uniform error of our learned solution path relative to the true path exhibits linear convergence to a constant related to the expressiveness of the basis. When the true solution path lies in the span of the basis, this constant is zero. We also prove stronger results for special cases common in machine learning: When $\lambda \in [-1, 1]$ and the solution path is $\nu$-times differentiable, constant step-size SGD learns a path with $\epsilon$ uniform error after at most $O(\epsilon^{\frac{1}{1-\nu}} \log(1/\epsilon))$ iterations, and when the solution path is analytic, it only requires $O\left(\log^2(1/\epsilon)\log\log(1/\epsilon)\right)$. By comparison, the best-known discretization schemes in these settings require at least $O(\epsilon^{-1/2})$ discretization points (and even more gradient calls). Finally, we propose an adaptive variant of our method that sequentially adds basis functions and demonstrates strong numerical performance through experiments.

The integration of autonomous driving technologies with vehicular networks presents significant challenges in privacy preservation, communication efficiency, and resource allocation. This paper proposes a novel U-shaped split federated learning (U-SFL) framework to address these challenges on the way of realizing in vehicular edge networks. U-SFL is able to enhance privacy protection by keeping both raw data and labels on the vehicular user (VU) side while enabling parallel processing across multiple vehicles. To optimize communication efficiency, we introduce a semantic-aware auto-encoder (SAE) that significantly reduces the dimensionality of transmitted data while preserving essential semantic information. Furthermore, we develop a deep reinforcement learning (DRL) based algorithm to solve the NP-hard problem of dynamic resource allocation and split point selection. Our comprehensive evaluation demonstrates that U-SFL achieves comparable classification performance to traditional split learning (SL) while substantially reducing data transmission volume and communication latency. The proposed DRL-based optimization algorithm shows good convergence in balancing latency, energy consumption, and learning performance.

While the Transformer architecture has achieved remarkable success across various domains, a thorough theoretical foundation explaining its optimization dynamics is yet to be fully developed. In this study, we aim to bridge this understanding gap by answering the following two core questions: (1) Which types of Transformer architectures allow Gradient Descent (GD) to achieve guaranteed convergence? and (2) Under what initial conditions and architectural specifics does the Transformer achieve rapid convergence during training? By analyzing the loss landscape of a single Transformer layer using Softmax and Gaussian attention kernels, our work provides concrete answers to these questions. Our findings demonstrate that, with appropriate weight initialization, GD can train a Transformer model (with either kernel type) to achieve a global optimal solution, especially when the input embedding dimension is large. Nonetheless, certain scenarios highlight potential pitfalls: training a Transformer using the Softmax attention kernel may sometimes lead to suboptimal local solutions. In contrast, the Gaussian attention kernel exhibits a much favorable behavior. Our empirical study further validate the theoretical findings.

In this work, we address unconstrained finite-sum optimization problems, with particular focus on instances originating in large scale deep learning scenarios. Our main interest lies in the exploration of the relationship between recent line search approaches for stochastic optimization in the overparametrized regime and momentum directions. First, we point out that combining these two elements with computational benefits is not straightforward. To this aim, we propose a solution based on mini-batch persistency. We then introduce an algorithmic framework that exploits a mix of data persistency, conjugate-gradient type rules for the definition of the momentum parameter and stochastic line searches. The resulting algorithm is empirically shown to outperform other popular methods from the literature, obtaining state-of-the-art results in both convex and nonconvex large scale training problems.

Managing resources effectively in uncertain demand, variable availability, and complex governance policies is a significant challenge. This paper presents a paradigmatic framework for addressing these issues in water management scenarios by integrating advanced physical modelling, remote sensing techniques, and Artificial Intelligence algorithms. The proposed approach accurately predicts water availability, estimates demand, and optimizes resource allocation on both short- and long-term basis, combining a comprehensive hydrological model, agronomic crop models for precise demand estimation, and Mixed-Integer Linear Programming for efficient resource distribution. In the study case of the Segura Hydrographic Basin, the approach successfully allocated approximately 642 million cubic meters ($hm^3$) of water over six months, minimizing the deficit to 9.7% of the total estimated demand. The methodology demonstrated significant environmental benefits, reducing CO2 emissions while optimizing resource distribution. This robust solution supports informed decision-making processes, ensuring sustainable water management across diverse contexts. The generalizability of this approach allows its adaptation to other basins, contributing to improved governance and policy implementation on a broader scale. Ultimately, the methodology has been validated and integrated into the operational water management practices in the Segura Hydrographic Basin in Spain.

Real-world graphs grow rapidly with edge and vertex insertions over time, motivating the problem of efficiently maintaining robust node representation over evolving graphs. Recent efficient GNNs are designed to decouple recursive message passing from the learning process, and favor Personalized PageRank (PPR) as the underlying feature propagation mechanism. However, most PPR-based GNNs are designed for static graphs, and efficient PPR maintenance remains as an open problem. Further, there is surprisingly little theoretical justification for the choice of PPR, despite its impressive empirical performance. In this paper, we are inspired by the recent PPR formulation as an explicit $\ell_1$-regularized optimization problem and propose a unified dynamic graph learning framework based on sparse node-wise attention. We also present a set of desired properties to justify the choice of PPR in STOA GNNs, and serves as the guideline for future node attention designs. Meanwhile, we take advantage of the PPR-equivalent optimization formulation and employ the proximal gradient method (ISTA) to improve the efficiency of PPR-based GNNs upto 6 times. Finally, we instantiate a simple-yet-effective model (\textsc{GoPPE}) with robust positional encodings by maximizing PPR previously used as attention. The model performs comparably to or better than the STOA baselines and greatly outperforms when the initial node attributes are noisy during graph evolution, demonstrating the effectiveness and robustness of \textsc{GoPPE}.

We focus on collaborative and federated black-box optimization (BBOpt), where agents optimize their heterogeneous black-box functions through collaborative sequential experimentation. From a Bayesian optimization perspective, we address the fundamental challenges of distributed experimentation, heterogeneity, and privacy within BBOpt, and propose three unifying frameworks to tackle these issues: (i) a global framework where experiments are centrally coordinated, (ii) a local framework that allows agents to make decisions based on minimal shared information, and (iii) a predictive framework that enhances local surrogates through collaboration to improve decision-making. We categorize existing methods within these frameworks and highlight key open questions to unlock the full potential of federated BBOpt. Our overarching goal is to shift federated learning from its predominantly descriptive/predictive paradigm to a prescriptive one, particularly in the context of BBOpt - an inherently sequential decision-making problem.

We consider a class of structured fractional minimization problems, where the numerator includes a differentiable function, a simple nonconvex nonsmooth function, a concave nonsmooth function, and a convex nonsmooth function composed with a linear operator, while the denominator is a continuous function that is either weakly convex or has a weakly convex square root. These problems are widespread and span numerous essential applications in machine learning and data science. Existing methods are mainly based on subgradient methods and smoothing proximal gradient methods, which may suffer from slow convergence and numerical stability issues. In this paper, we introduce {\sf FADMM}, the first Alternating Direction Method of Multipliers tailored for this class of problems. {\sf FADMM} decouples the original problem into linearized proximal subproblems, featuring two variants: one using Dinkelbach's parametric method ({\sf FADMM-D}) and the other using the quadratic transform method ({\sf FADMM-Q}). By introducing a novel Lyapunov function, we establish that {\sf FADMM} converges to $\epsilon$-approximate critical points of the problem within an oracle complexity of $\mathcal{O}(1/\epsilon^{3})$. Our experiments on synthetic and real-world data for sparse Fisher discriminant analysis, robust Sharpe ratio minimization, and robust sparse recovery demonstrate the effectiveness of our approach. Keywords: Fractional Minimization, Nonconvex Optimization, Proximal Linearized ADMM, Nonsmooth Optimization, Convergence Analysis

Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar loss function but instead correspond to solving a variational inequality (VI) problem. This difference in setting has caused many practical challenges as naive gradient-based approaches from supervised learning tend to diverge and cycle in the VI case. In this work, we propose a principled surrogate-based approach compatible with deep learning to solve VIs. We show that our surrogate-based approach has three main benefits: (1) under assumptions that are realistic in practice (when hidden monotone structure is present, interpolation, and sufficient optimization of the surrogates), it guarantees convergence, (2) it provides a unifying perspective of existing methods, and (3) is amenable to existing deep learning optimizers like ADAM. Experimentally, we demonstrate our surrogate-based approach is effective in min-max optimization and minimizing projected Bellman error. Furthermore, in the deep reinforcement learning case, we propose a novel variant of TD(0) which is more compute and sample efficient.