We propose an RNN-based efficient Ising model solver, the Criticality-ordered Recurrent Mean On one hand, the connection between NP problems and Field (CoRMF), for forward Ising problems. In Ising models has resulted in strong physics intuitions [Kirkpatrick its core, a criticality-ordered spin sequence of et al., 1983] that the hardness of these problems an N-spin Ising model is introduced by sorting emerges through the lens of complex energy landscapes mission-critical edges with greedy algorithm, over discrete random variables with multiple local minima such that an autoregressive mean-field factorization [Barahona, 1982, Chowdhury, 2014]. On the other hand, can be utilized and optimized with Recurrent the computational difficulty on the Ising side resonates with Neural Networks (RNNs). Our method the difficulties of numerous significant scientific problems, has two notable characteristics: (i) by leveraging including numerous other combinatorial decision-making the approximated tree structure of the underlying and optimization problems [Benati and Rizzi, 2007, Ngo Ising graph, the newly-obtained criticality et al., 1994, Garey and Johnson, 1979]. As the opposite order enables the unification between variational of conventional inverse Ising problems [Nguyen et al., mean-field and RNN, allowing the generally 2017, Reneau et al., 2023] that reconstruct graphical structure intractable Ising model to be efficiently from data, we refer to these problems, which have probed with probabilistic inference; (ii) it is wellmodulized, pre-specified graphical structures, as forward Ising problems model-independent while at the same (combinatorial inference and optimization problems time expressive enough, and hence fully applicable in Ising formulations [De las Cuevas and Cubitt, 2016, Lucas, to any forward Ising inference problems 2014, Pan et al., 2023]), and any efficient computational with minimal effort. Computationally, by using method or hardware solver [Mohseni et al., 2022] a variance-reduced Monte Carlo gradient estimator, for Ising models can potentially benefit them. CoRFM solves the Ising problems in a selftrain To describe the Ising model, we first introduce some notation fashion without data/evidence, and the inference here. We consider an Ising model of N spins as an exponential family model for binary N-spin data up to tasks can be executed by directly sampling quadratic sufficient statistic taking the Boltzmann form from RNN. Theoretically, we establish a provably tighter error bound than naive meanfield

The optimization of a black-box simulator over control parameters $\mathbf{x}$ arises in a myriad of scientific applications. In such applications, the simulator often takes the form $f(\mathbf{x},\boldsymbol{\theta})$, where $\boldsymbol{\theta}$ are parameters that are uncertain in practice. Robust optimization aims to optimize the objective $\mathbb{E}[f(\mathbf{x},\boldsymbol{\Theta})]$, where $\boldsymbol{\Theta} \sim \mathcal{P}$ is a random variable that models uncertainty on $\boldsymbol{\theta}$. For this, existing black-box methods typically employ a two-stage approach for selecting the next point $(\mathbf{x},\boldsymbol{\theta})$, where $\mathbf{x}$ and $\boldsymbol{\theta}$ are optimized separately via different acquisition functions. As such, these approaches do not employ a joint acquisition over $(\mathbf{x},\boldsymbol{\theta})$, and thus may fail to fully exploit control-to-noise interactions for effective robust optimization. To address this, we propose a new Bayesian optimization method called Targeted Variance Reduction (TVR). The TVR leverages a novel joint acquisition function over $(\mathbf{x},\boldsymbol{\theta})$, which targets variance reduction on the objective within the desired region of improvement. Under a Gaussian process surrogate on $f$, the TVR acquisition can be evaluated in closed form, and reveals an insightful exploration-exploitation-precision trade-off for robust black-box optimization. The TVR can further accommodate a broad class of non-Gaussian distributions on $\mathcal{P}$ via a careful integration of normalizing flows. We demonstrate the improved performance of TVR over the state-of-the-art in a suite of numerical experiments and an application to the robust design of automobile brake discs under operational uncertainty.

Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling the target-ligand distribution can hardly fulfill one of the main goals in drug discovery -- designing novel ligands with desired properties, e.g., high binding affinity, easily synthesizable, etc. This challenge becomes particularly pronounced when the target-ligand pairs used for training do not align with these desired properties. Moreover, most existing methods aim at solving \textit{de novo} design task, while many generative scenarios requiring flexible controllability, such as R-group optimization and scaffold hopping, have received little attention. In this work, we propose DecompOpt, a structure-based molecular optimization method based on a controllable and decomposed diffusion model. DecompOpt presents a new generation paradigm which combines optimization with conditional diffusion models to achieve desired properties while adhering to the molecular grammar. Additionally, DecompOpt offers a unified framework covering both \textit{de novo} design and controllable generation. To achieve so, ligands are decomposed into substructures which allows fine-grained control and local optimization. Experiments show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines, and demonstrate great potential in controllable generation tasks.

Abrupt maneuvers by surrounding vehicles (SVs) can typically lead to safety concerns and affect the task efficiency of the ego vehicle (EV), especially with model uncertainties stemming from environmental disturbances. This paper presents a real-time fail-operational controller that ensures the asymptotic convergence of an uncertain EV to a safe state, while preserving task efficiency in dynamic environments. An incremental Bayesian learning approach is developed to facilitate online learning and inference of changing environmental disturbances. Leveraging disturbance quantification and constraint transformation, we develop a stochastic fail-operational barrier based on the control barrier function (CBF). With this development, the uncertain EV is able to converge asymptotically from an unsafe state to a defined safe state with probabilistic stability. Subsequently, the stochastic fail-operational barrier is integrated into an efficient fail-operational controller based on quadratic programming (QP). This controller is tailored for the EV operating under control constraints in the presence of environmental disturbances, with both safety and efficiency objectives taken into consideration. We validate the proposed framework in connected cruise control (CCC) tasks, where SVs perform aggressive driving maneuvers. The simulation results demonstrate that our method empowers the EV to swiftly return to a safe state while upholding task efficiency in real time, even under time-varying environmental disturbances.

Due to the recent increase in interest in Financial Technology (FinTech), applications like credit default prediction (CDP) are gaining significant industrial and academic attention. In this regard, CDP plays a crucial role in assessing the creditworthiness of individuals and businesses, enabling lenders to make informed decisions regarding loan approvals and risk management. In this paper, we propose a workflow-based approach to improve CDP, which refers to the task of assessing the probability that a borrower will default on his or her credit obligations. The workflow consists of multiple steps, each designed to leverage the strengths of different techniques featured in machine learning pipelines and, thus best solve the CDP task. We employ a comprehensive and systematic approach starting with data preprocessing using Weight of Evidence encoding, a technique that ensures in a single-shot data scaling by removing outliers, handling missing values, and making data uniform for models working with different data types. Next, we train several families of learning models, introducing ensemble techniques to build more robust models and hyperparameter optimization via multi-objective genetic algorithms to consider both predictive accuracy and financial aspects. Our research aims at contributing to the FinTech industry in providing a tool to move toward more accurate and reliable credit risk assessment, benefiting both lenders and borrowers.

One way to avoid global smoothness of f is to use local Lipschitz continuity of the gradient ("local smoothness"). Local We develop new sub-optimality bounds for gradient smoothness uses different Lipschitz constants for different descent (GD) that depend on the conditioning neighbourhoods, thus avoiding global assumptions and obtaining of the objective along the path of optimization, improved rates. However, such analyses typically require rather than on global, worst-case constants. Key the iterates to be bounded, in which case local smoothness to our proofs is directional smoothness, a measure reduces to L-smoothness over a compact set (Malitsky of gradient variation that we use to develop upperbounds & Mishchenko, 2020). Boundedness can be enforced in a on the objective. Minimizing these upperbounds variety of ways: Zhang & Hong (2020) break optimization requires solving implicit equations to obtain into stages, Patel & Berahas (2022) develop a stopping-time a sequence of strongly adapted step-sizes; framework, and Lu & Mei (2023) use line-search and a modified we show that these equations are straightforward update. These approaches either modify the underlying to solve for convex quadratics and lead to new optimization algorithm, require local smoothness oracles guarantees for two classical step-sizes. For general (Park et al., 2021), or rely on highly complex arguments.

In this paper, we propose an approach for identifying linear and nonlinear discrete-time state-space models, possibly under $\ell_1$- and group-Lasso regularization, based on the L-BFGS-B algorithm. For the identification of linear models, we show that, compared to classical linear subspace methods, the approach often provides better results, is much more general in terms of the loss and regularization terms used, and is also more stable from a numerical point of view. The proposed method not only enriches the existing set of linear system identification tools but can be also applied to identifying a very broad class of parametric nonlinear state-space models, including recurrent neural networks. We illustrate the approach on synthetic and experimental datasets and apply it to solve the challenging industrial robot benchmark for nonlinear multi-input/multi-output system identification proposed by Weigand et al. (2022). A Python implementation of the proposed identification method is available in the package \texttt{jax-sysid}, available at \url{https://github.com/bemporad/jax-sysid}.

In quantum computing, we are capable not only of transforming states but also of transforming processes. Designing quantum circuits to transform input operations has a wide range of applications in quantum computing, quantum information processing, and quantum machine learning. The networks that perform such transformations are known as super-channels [1, 2], which take processes as inputs and output the corresponding transformed process. In general, all these super-channels can be realized with the quantum comb architecture [1, 2]. Figure 1 illustrates an example where a quantum comb takes m quantum operations as input and outputs a target new operation. Quantum comb is widely applied in solving process transformation problems and optimizing the ultimate achievable performance, including transformations of unitary operations such as inversion [3, 4], complex conjugation, control-U analysis [5], as well as learning tasks [6, 7]. It can also be used for analyzing more general processes [8] and has also inspired structures like the indefinite causal network [9, 10]. However, obtaining the explicit quantum circuit required for the desired transformation is a challenging problem. A major problem of the semidefinite programming (SDP) approach based on the Choi-Jamiołkowski isomorphism is that the dimension of the Choi operator of the quantum comb, i.e., the dimension of the variable in such SDP problems, grows exponentially fast with the increase in the number of comb slots. Another issue is that the SDP ultimately returns the Choi operator of the quantum comb; however, finding a physical implementation of this network, such as converting it into a standard circuit model, is not straightforward.

The conjunction of edge intelligence and the ever-growing Internet-of-Things (IoT) network heralds a new era of collaborative machine learning, with federated learning (FL) emerging as the most prominent paradigm. With the growing interest in these learning schemes, researchers started addressing some of their most fundamental limitations. Indeed, conventional FL with a central aggregator presents a single point of failure and a network bottleneck. To bypass this issue, decentralized FL where nodes collaborate in a peer-to-peer network has been proposed. Despite the latter's efficiency, communication costs and data heterogeneity remain key challenges in decentralized FL. In this context, we propose a novel scheme, called opportunistic communication-efficient decentralized federated learning, a.k.a., OCD-FL, consisting of a systematic FL peer selection for collaboration, aiming to achieve maximum FL knowledge gain while reducing energy consumption. Experimental results demonstrate the capability of OCD-FL to achieve similar or better performances than the fully collaborative FL, while significantly reducing consumed energy by at least 30% and up to 80%.

Optimizing the performance of many objectives (instantiated by tasks or clients) jointly with a few Pareto stationary solutions (models) is critical in machine learning. However, previous multi-objective optimization methods often focus on a few number of objectives and cannot scale to many objectives that outnumber the solutions, leading to either subpar performance or ignored objectives. We introduce Many-objective multi-solution Transport (MosT), a framework that finds multiple diverse solutions in the Pareto front of many objectives. Our insight is to seek multiple solutions, each performing as a domain expert and focusing on a specific subset of objectives while collectively covering all of them. MosT formulates the problem as a bi-level optimization of weighted objectives for each solution, where the weights are defined by an optimal transport between the objectives and solutions. Our algorithm ensures convergence to Pareto stationary solutions for complementary subsets of objectives. On a range of applications in federated learning, multi-task learning, and mixture-of-prompt learning for LLMs, MosT distinctly outperforms strong baselines, delivering high-quality, diverse solutions that profile the entire Pareto frontier, thus ensuring balanced trade-offs across many objectives.