Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations. Although it achieves superiority in simulation accuracy, the tremendous computational cost makes it unbearable for high-throughput simulation tasks such as sensitivity analysis, inverse design, etc. In this work, we propose AD-NEGF, to our best knowledge the first end-to-end differentiable NEGF model for quantum transport simulations. We implement the entire numerical process in PyTorch, and design customized backward pass with implicit layer techniques, which provides gradient information at an affordable cost while guaranteeing the correctness of the forward simulation. The proposed model is validated with applications in calculating differential physical quantities, empirical parameter fitting, and doping optimization, which demonstrates its capacity to accelerate the material design process by conducting gradient-based parameter optimization.

We propose and implement an interpretable machine learning classification model for Explainable AI (XAI) based on expressive Boolean formulas. Potential applications include credit scoring and diagnosis of medical conditions. The Boolean formula defines a rule with tunable complexity (or interpretability), according to which input data are classified. Such a formula can include any operator that can be applied to one or more Boolean variables, thus providing higher expressivity compared to more rigid rule-based and tree-based approaches. The classifier is trained using native local optimization techniques, efficiently searching the space of feasible formulas. Shallow rules can be determined by fast Integer Linear Programming (ILP) or Quadratic Unconstrained Binary Optimization (QUBO) solvers, potentially powered by special purpose hardware or quantum devices. We combine the expressivity and efficiency of the native local optimizer with the fast operation of these devices by executing non-local moves that optimize over subtrees of the full Boolean formula. We provide extensive numerical benchmarking results featuring several baselines on well-known public datasets. Based on the results, we find that the native local rule classifier is generally competitive with the other classifiers. The addition of non-local moves achieves similar results with fewer iterations, and therefore using specialized or quantum hardware could lead to a speedup by fast proposal of non-local moves.

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed. Given gradient information in a high dimension $d$, the agent passes the compressed information processed by a sketching matrix $R\in \mathbb{R}^{s\times d}$ with $s\ll d$, and the receiver de-compressed via the de-sketching matrix $R^\top$ to ``recover'' the information in original dimension. Using such a framework, we develop algorithms for federated learning with lower communication costs. However, such random sketching does not protect the privacy of local data directly. We show that the gradient leakage problem still exists after applying the sketching technique by presenting a specific gradient attack method. As a remedy, we prove rigorously that the algorithm will be differentially private by adding additional random noises in gradient information, which results in a both communication-efficient and differentially private first order approach for federated learning tasks. Our sketching scheme can be further generalized to other learning settings and might be of independent interest itself.

Generalization performance is a key metric in evaluating machine learning models when applied to real-world applications. Good generalization indicates the model can predict unseen data correctly when trained under a limited number of data. Federated learning (FL), which has emerged as a popular distributed learning framework, allows multiple devices or clients to train a shared model without violating privacy requirements. While the existing literature has studied extensively the generalization performances of centralized machine learning algorithms, similar analysis in the federated settings is either absent or with very restrictive assumptions on the loss functions. In this paper, we aim to analyze the generalization performances of federated learning by means of algorithmic stability, which measures the change of the output model of an algorithm when perturbing one data point. Three widely-used algorithms are studied, including FedAvg, SCAFFOLD, and FedProx, under convex and non-convex loss functions. Our analysis shows that the generalization performances of models trained by these three algorithms are closely related to the heterogeneity of clients' datasets as well as the convergence behaviors of the algorithms. Particularly, in the i.i.d. setting, our results recover the classical results of stochastic gradient descent (SGD).

These optimization problems offer a means to model highly intricate discrete decision problems across diverse domains where pairwise interactions play a crucial role, such as social network analysis [1], wireless communications [2], operations research [3], scheduling [4], and transportation [5]. A considerable portion of these problems belongs to the broader class of NP-hard problems, where it is challenging to find exact solutions, as doing so often necessitates a near-complete enumeration of the entire search space. Consequently, computation of exact solutions is practically infeasible, and approximation or heuristic algorithms are generally favored for practical applications. Although these algorithms exhibit significantly faster runtime and possess sub-exponential theoretical complexities, they often yield suboptimal solutions. Therefore, a key area of research revolves around the development of approximation or heuristic algorithms that can provide solutions that are as close to optimal as possible. The minimum dominating set (MDS) problem is an important network-based optimization problem that involves finding the smallest dominating set of a given graph. A dominating set of a graph is a subset of the vertices in the graph such that every vertex is either in the dominating set or adjacent to a vertex in the dominating set. The MDS problem aims to find the dominating set of minimum cardinality. Dominating sets have a wide range of applications in various fields, including social networks [6-8], cybersecurity [9], biological networks [10], bioinformatics [11], multi-document summarization [12], and wireless sensor networks [13]

We study the multi-objective minimum weight base problem, an abstraction of classical NP-hard combinatorial problems such as the multi-objective minimum spanning tree problem. We prove some important properties of the convex hull of the non-dominated front, such as its approximation quality and an upper bound on the number of extreme points. Using these properties, we give the first run-time analysis of the MOEA/D algorithm for this problem, an evolutionary algorithm that effectively optimizes by decomposing the objectives into single-objective components. We show that the MOEA/D, given an appropriate decomposition setting, finds all extreme points within expected fixed-parameter polynomial time in the oracle model, the parameter being the number of objectives. Experiments are conducted on random bi-objective minimum spanning tree instances, and the results agree with our theoretical findings. Furthermore, compared with a previously studied evolutionary algorithm for the problem GSEMO, MOEA/D finds all extreme points much faster across all instances.

Balanced circular bin packing problems consist in positioning a given number of weighted circles in order to minimize the radius of a circular container while satisfying equilibrium constraints. These problems are NP-hard, highly constrained and dimensional. This paper describes a swarm algorithm based on a virtual-force system in order to solve balanced circular bin packing problems. In the proposed approach, a system of forces is applied to each component allowing to take into account the constraints and minimizing the objective function using the fundamental principle of dynamics. The proposed algorithm is experimented and validated on benchmarks of various balanced circular bin packing problems with up to 300 circles. The reported results allow to assess the effectiveness of the proposed approach compared to existing results from the literature.

We consider the problem of assigning items to platforms while satisfying group and individual fairness constraints. Each item is associated with certain groups and has a preference ordering over platforms. Each platform enforces group fairness by specifying an upper and a lower bound on the number of items that can be matched to it from each group. Although there may be multiple optimal solutions that satisfy the group fairness constraints, we aim to achieve `probabilistic individual fairness' by computing a distribution over `group fair' matchings such that each item has a reasonable probability of being matched to one of its top choices. When each item can belong to multiple groups, the problem of finding a maximum size group-fair matching is NP-hard even when all the group lower bounds are 0, and there are no individual fairness constraints. Given a total of $n$ items, we achieve a $O(\Delta \log n)$ approximation algorithm when an item can belong to at most $\Delta$ groups, and all the group lower bounds are 0. We also provide two approximation algorithms in terms of the total number of groups that have items in the neighborhood of a platform. When each item belongs to a single group, we provide a polynomial-time algorithm that computes a probabilistic individually fair distribution over group fair matching. We further extend our model and algorithms to address the following notions of fairness: `maxmin group fairness', which maximizes the representation of the worst-off groups, and `mindom group fairness', which minimizes the representation of the most dominant groups.

Caches are deployed at many different levels in computer systems: from CPU hardware caches to operating system memory caches, from application caches at clients to CDN caches deployed as physical servers in the network or as cloud services like Amazon's ElastiCache [1]. They aim to provide faster service to the user and/or to reduce the computation/communication load on other system elements, like hard disks, file servers, etc. The ubiquity of caches has motivated extensive research on the performance of existing caching policies, as well as on the design of new policies with provable guarantees. To that end, most prior work has assumed that caches serve requests generated according to a stochastic process, ranging from the simple, memory-less independent reference model [2] to more complex models trying to capture temporal locality effects and time-varying popularities (e.g., the shot-noise model [3]). An alternative modeling approach is to consider an adversarial setting.

Topology optimization (TO) is a method of deriving an optimal design that satisfies a given load and boundary conditions within a design domain. This method enables effective design without initial design, but has been limited in use due to high computational costs. At the same time, machine learning (ML) methodology including deep learning has made great progress in the 21st century, and accordingly, many studies have been conducted to enable effective and rapid optimization by applying ML to TO. Therefore, this study reviews and analyzes previous research on ML-based TO (MLTO). Two different perspectives of MLTO are used to review studies: (1) TO and (2) ML perspectives. The TO perspective addresses "why" to use ML for TO, while the ML perspective addresses "how" to apply ML to TO. In addition, the limitations of current MLTO research and future research directions are examined.