We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading to very limited certifying performance. In this paper, we present the first collective certificate, which certifies a set of target nodes simultaneously. To achieve it, we formulate the problem as a binary integer quadratic constrained linear programming (BQCLP). We further develop a customized linearization technique that allows us to relax the BQCLP into linear programming (LP) that can be efficiently solved. Through comprehensive experiments, we demonstrate that our collective certification scheme significantly improves certification performance with minimal computational overhead. For instance, by solving the LP within 1 minute on the Citeseer dataset, we achieve a significant increase in the certified ratio from 0.0% to 81.2% when the injected node number is 5% of the graph size. Our step marks a crucial step towards making provable defense more practical.

This paper introduces the Capacitated Covering Salesman Problem (CCSP), approaching the notion of service by coverage in capacitated vehicle routing problems. In CCSP, locations where vehicles can transit are provided, some of which have customers with demands. The objective is to service customers through a fleet of vehicles based in a depot, minimizing the total distance traversed by the vehicles. CCSP is unique in the sense that customers, to be serviced, do not need to be visited by a vehicle. Instead, they can be serviced if they are within a coverage area of the vehicle. This assumption is motivated by applications in which some customers are unreachable (e.g., forbidden access to vehicles) or visiting every customer is impractical. In this work, optimization methodologies are proposed for the CCSP based on ILP (Integer Linear Programming) and BRKGA (Biased Random-Key Genetic Algorithm) metaheuristic. Computational experiments conducted on a benchmark of instances for the CCSP evaluate the performance of the methodologies with respect to primal bounds. Furthermore, our ILP formulation is extended in order to create a novel MILP (Mixed Integer Linear Programming) for the Multi-Depot Covering Tour Vehicle Routing Problem (MDCTVRP). Computational experiments show that the extended MILP formulation outperformed the previous state-of-the-art exact approach with respect to optimality gaps. In particular, optimal solutions were obtained for several previously unsolved instances.

This paper presents a novel hierarchical federated learning algorithm within multiple sets that incorporates quantization for communication-efficiency and demonstrates resilience to statistical heterogeneity. Unlike conventional hierarchical federated learning algorithms, our approach combines gradient aggregation in intra-set iterations with model aggregation in inter-set iterations. We offer a comprehensive analytical framework to evaluate its optimality gap and convergence rate, comparing these aspects with those of conventional algorithms. Additionally, we develop a problem formulation to derive optimal system parameters in a closed-form solution. Our findings reveal that our algorithm consistently achieves high learning accuracy over a range of parameters and significantly outperforms other hierarchical algorithms, particularly in scenarios with heterogeneous data distributions.

Ergodic search enables optimal exploration of an information distribution while guaranteeing the asymptotic coverage of the search space. However, current methods typically have exponential computation complexity in the search space dimension and are restricted to Euclidean space. We introduce a computationally efficient ergodic search method. Our contributions are two-fold. First, we develop a kernel-based ergodic metric and generalize it from Euclidean space to Lie groups. We formally prove the proposed metric is consistent with the standard ergodic metric while guaranteeing linear complexity in the search space dimension. Secondly, we derive the first-order optimality condition of the kernel ergodic metric for nonlinear systems, which enables efficient trajectory optimization. Comprehensive numerical benchmarks show that the proposed method is at least two orders of magnitude faster than the state-of-the-art algorithm. Finally, we demonstrate the proposed algorithm with a peg-in-hole insertion task. We formulate the problem as a coverage task in the space of SE(3) and use a 30-second-long human demonstration as the prior distribution for ergodic coverage. Ergodicity guarantees the asymptotic solution of the peg-in-hole problem so long as the solution resides within the prior information distribution, which is seen in the 100\% success rate.

This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning of LMs. We first propose an objective that optimizes LM learning by maximizing the data compression ratio in an "LM-training-as-lossless-compression" view. Then, we derive a theorem, named Learning Law, to reveal the properties of the dynamics in the optimal learning process under our objective. The theorem is then validated by experiments on a linear classification and a real-world language modeling task. Finally, we empirically verify that the optimal learning of LMs essentially stems from the improvement of the coefficients in the scaling law of LMs, indicating great promise and significance for designing practical learning acceleration methods. Our code can be found at https://aka.ms/LearningLaw.

Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways; meanwhile offering valuable insights into other systems incorporating SE(3)-invariance.

Structured pruning is a promising approach for reducing the inference costs of large vision and language models. By removing carefully chosen structures, e.g., neurons or attention heads, the improvements from this approach can be realized on standard deep learning hardware. In this work, we focus on structured pruning in the one-shot (post-training) setting, which does not require model retraining after pruning. We propose a novel combinatorial optimization framework for this problem, based on a layer-wise reconstruction objective and a careful reformulation that allows for scalable optimization. Moreover, we design a new local combinatorial optimization algorithm, which exploits low-rank updates for efficient local search. Our framework is time and memory-efficient and considerably improves upon state-of-the-art one-shot methods on vision models (e.g., ResNet50, MobileNet) and language models (e.g., OPT-1.3B -- OPT-30B). For language models, e.g., OPT-2.7B, OSSCAR can lead to $125\times$ lower test perplexity on WikiText with $2\times$ inference time speedup in comparison to the state-of-the-art ZipLM approach. Our framework is also $6\times$ -- $8\times$ faster. Notably, our work considers models with tens of billions of parameters, which is up to $100\times$ larger than what has been previously considered in the structured pruning literature.

A user-centric design and resource optimization should be at the center of any technology or innovation. The user-centric perspective gives the developer the opportunity to develop with task-based optimization. The user in the medical image field is a medical professional who analyzes the medical images and gives their diagnosis results to the patient. This scheme, having the medical professional user's perspective, innovates in the area of Medical Image storage and security. The architecture is designed with three main segments, namely: Segmentation, Storage, and Retrieval. This architecture was designed owing to the fact that the number of retrieval operations done by medical professionals was toweringly higher when compared to the storage operations done for some handful number of times for a particular medical image. This gives room for our innovation to segment out the medically indispensable part of the medical image, encrypt it, and store it. By encrypting the vital parts of the image using a strong encryption algorithm like the chaotic Henon map, we are able to keep the security intact. Now retrieving the medical image demands only the computationally less stressing decryption of the segmented region of interest. The decryption of the segmented region of interest results in the full recovery of the medical image which can be viewed on demand by the medical professionals for various diagnosis purposes. In this scheme, we were able to achieve a retrieval speed improvement of around 47% when compared to a full image encryption of brain medical CT images.

Abstract--This work reports a novel Bundle Adjustment (BA) formulation using a Reproducing Kernel Hilbert Space (RKHS) representation called RKHS-BA. The proposed formulation is correspondence-free, enables the BA to use RGB-D/LiDAR and semantic labels in the optimization directly, and provides a generalization for the photometric loss function commonly used in direct methods. RKHS-BA can incorporate appearance and semantic labels within a continuous spatial-semantic functional representation that does not require optimization via image pyramids. We demonstrate its applications in sliding-window odometry and global LiDAR mapping, which show highly robust performance in extremely challenging scenes and the best tradeoff of generalization and accuracy. I. INTRODUCTION Bundle Adjustment (BA) is widely used in visual perception algorithms such as Simultaneous Localization and Mapping (SLAM) and 3D Reconstruction. It jointly optimizes visual structures and all the camera parameters to construct a spatially-consistent 3D world model [73]. Then, in the optimization step, they minimize reprojected geometric residuals for features observed across multiple frames via multi-view geometry [36, 73]. However, full images need to be stored in the to sparse Hessian structures but relies on correct feature pose graph even in semi-dense approaches [95]. Many works have their illumination invariance presumption is seriously violated been devoted to improving their robustness, such as improving in outdoor situations where complex illumination, changeable frontend feature matching's quality with deep networks [33], weather, and dynamic objects exist. Specifically, we denote various types of visual information, feature association contaminated with outliers is still an open including pixel classes, object instances, intensities, problem [56].

Thompson sampling (TS) serves as a solution for addressing the exploitation-exploration dilemma in Bayesian optimization (BO). While it prioritizes exploration by randomly generating and maximizing sample paths of Gaussian process (GP) posteriors, TS weakly manages its exploitation by gathering information about the true objective function after each exploration is performed. In this study, we incorporate the epsilon-greedy ($\varepsilon$-greedy) policy, a well-established selection strategy in reinforcement learning, into TS to improve its exploitation. We first delineate two extremes of TS applied for BO, namely the generic TS and a sample-average TS. The former and latter promote exploration and exploitation, respectively. We then use $\varepsilon$-greedy policy to randomly switch between the two extremes. A small value of $\varepsilon \in (0,1)$ prioritizes exploitation, and vice versa. We empirically show that $\varepsilon$-greedy TS with an appropriate $\varepsilon$ is better than one of its two extremes and competes with the other.