In this work, we close the fundamental gap of theory and practice by providing an improved regret bound for linear ensemble sampling. We prove that with an ensemble size logarithmic in $T$, linear ensemble sampling can achieve a frequentist regret bound of $\tilde{\mathcal{O}}(d^{3/2}\sqrt{T})$, matching state-of-the-art results for randomized linear bandit algorithms, where $d$ and $T$ are the dimension of the parameter and the time horizon respectively. Our approach introduces a general regret analysis framework for linear bandit algorithms. Additionally, we reveal a significant relationship between linear ensemble sampling and Linear Perturbed-History Exploration (LinPHE), showing that LinPHE is a special case of linear ensemble sampling when the ensemble size equals $T$. This insight allows us to derive a new regret bound of $\tilde{\mathcal{O}}(d^{3/2}\sqrt{T})$ for LinPHE, independent of the number of arms. Our contributions advance the theoretical foundation of ensemble sampling, bringing its regret bounds in line with the best known bounds for other randomized exploration algorithms.
相關內容
Photoacoustic imaging (PAI) suffers from inherent limitations that can degrade the quality of reconstructed results, such as noise, artifacts and incomplete data acquisition caused by sparse sampling or partial array detection. In this study, we proposed a new optimization method for both two-dimensional (2D) and three-dimensional (3D) PAI reconstruction results, called the regularized iteration method with shape prior. The shape prior is a probability matrix derived from the reconstruction results of multiple sets of random partial array signals in a computational imaging system using any reconstruction algorithm, such as Delay-and-Sum (DAS) and Back-Projection (BP). In the probability matrix, high-probability locations indicate high consistency among multiple reconstruction results at those positions, suggesting a high likelihood of representing the true imaging results. In contrast, low-probability locations indicate higher randomness, leaning more towards noise or artifacts. As a shape prior, this probability matrix guides the iteration and regularization of the entire array signal reconstruction results using the original reconstruction algorithm (the same algorithm for processing random partial array signals). The method takes advantage of the property that the similarity of the object to be imitated is higher than that of noise or artifact in the results reconstructed by multiple sets of random partial array signals of the entire imaging system. The probability matrix is taken as a prerequisite for improving the original reconstruction results, and the optimizer is used to further iterate the imaging results to remove noise and artifacts and improve the imaging fidelity. Especially in the case involving sparse view which brings more artifacts, the effect is remarkable. Simulation and real experiments have both demonstrated the superiority of this method.
In the context of communication complexity, we explore randomized protocols for graph coloring, focusing specifically on the vertex and edge coloring problems in $n$-vertex graphs $G$ with a maximum degree $\Delta$. We consider a scenario where the edges of $G$ are partitioned between two players. Our first contribution is a randomized protocol that efficiently finds a $(\Delta + 1)$-vertex coloring of $G$, utilizing $O(n)$ bits of communication in expectation and completing in $O(\log \log n \cdot \log \Delta)$ rounds in the worst case. This advancement represents a significant improvement over the work of Flin and Mittal [PODC 2024], who achieved the same communication cost but required $O(n)$ rounds in expectation, thereby making a significant reduction in the round complexity. We also present a randomized protocol for a $(2\Delta - 1)$-edge coloring of $G$, which maintains the same $O(n)$ bits of communication in expectation over $O(\log^\ast \Delta)$ rounds in the worst case. We complement the result with a tight $\Omega(n)$-bit lower bound on the communication complexity of the $(2\Delta-1)$-edge coloring, while a similar $\Omega(n)$ lower bound for the $(\Delta+1)$-vertex coloring has been established by Flin and Mittal [PODC 2024].
We study the problem of robust influence maximization in dynamic diffusion networks. In line with recent works, we consider the scenario where the network can undergo insertion and removal of nodes and edges, in discrete time steps, and the influence weights are determined by the features of the corresponding nodes and a global hyperparameter. Given this, our goal is to find, at every time step, the seed set maximizing the worst-case influence spread across all possible values of the hyperparameter. We propose an approximate solution using multiplicative weight updates and a greedy algorithm, with provable quality guarantees. Our experiments validate the effectiveness and efficiency of the proposed methods.
We introduce a new nonparametric causal decomposition approach that identifies the mechanisms by which a treatment variable contributes to a group-based outcome disparity. Our approach distinguishes three mechanisms: group differences in 1) treatment prevalence, 2) average treatment effects, and 3) selection into treatment based on individual-level treatment effects. Our approach reformulates classic Kitagawa-Blinder-Oaxaca decompositions in causal and nonparametric terms, complements causal mediation analysis by explaining group disparities instead of group effects, and isolates conceptually distinct mechanisms conflated in recent random equalization decompositions. In contrast to all prior approaches, our framework uniquely identifies differential selection into treatment as a novel disparity-generating mechanism. Our approach can be used for both the retrospective causal explanation of disparities and the prospective planning of interventions to change disparities. We present both an unconditional and a conditional decomposition, where the latter quantifies the contributions of the treatment within levels of certain covariates. We develop nonparametric estimators that are $\sqrt{n}$-consistent, asymptotically normal, semiparametrically efficient, and multiply robust. We apply our approach to analyze the mechanisms by which college graduation causally contributes to intergenerational income persistence (the disparity in adult income between the children of high- vs low-income parents). Empirically, we demonstrate a previously undiscovered role played by the new selection component in intergenerational income persistence.
Motivated by the change-making problem, we extend the notion of greediness to sets of positive integers not containing the element $1$, and from there to numerical semigroups. We provide an algorithm to determine if a given set (not necessarily containing the number $1$) is greedy. We also give specific conditions for sets of cardinality three, and we prove that numerical semigroups generated by three consecutive integers are greedy.
This work uniquely identifies and characterizes four prevalent multimodal model architectural patterns in the contemporary multimodal landscape. Systematically categorizing models by architecture type facilitates monitoring of developments in the multimodal domain. Distinct from recent survey papers that present general information on multimodal architectures, this research conducts a comprehensive exploration of architectural details and identifies four specific architectural types. The types are distinguished by their respective methodologies for integrating multimodal inputs into the deep neural network model. The first two types (Type A and B) deeply fuses multimodal inputs within the internal layers of the model, whereas the following two types (Type C and D) facilitate early fusion at the input stage. Type-A employs standard cross-attention, whereas Type-B utilizes custom-designed layers for modality fusion within the internal layers. On the other hand, Type-C utilizes modality-specific encoders, while Type-D leverages tokenizers to process the modalities at the model's input stage. The identified architecture types aid the monitoring of any-to-any multimodal model development. Notably, Type-C and Type-D are currently favored in the construction of any-to-any multimodal models. Type-C, distinguished by its non-tokenizing multimodal model architecture, is emerging as a viable alternative to Type-D, which utilizes input-tokenizing techniques. To assist in model selection, this work highlights the advantages and disadvantages of each architecture type based on data and compute requirements, architecture complexity, scalability, simplification of adding modalities, training objectives, and any-to-any multimodal generation capability.
Large Language Models (LLMs) have shown excellent generalization capabilities that have led to the development of numerous models. These models propose various new architectures, tweaking existing architectures with refined training strategies, increasing context length, using high-quality training data, and increasing training time to outperform baselines. Analyzing new developments is crucial for identifying changes that enhance training stability and improve generalization in LLMs. This survey paper comprehensively analyses the LLMs architectures and their categorization, training strategies, training datasets, and performance evaluations and discusses future research directions. Moreover, the paper also discusses the basic building blocks and concepts behind LLMs, followed by a complete overview of LLMs, including their important features and functions. Finally, the paper summarizes significant findings from LLM research and consolidates essential architectural and training strategies for developing advanced LLMs. Given the continuous advancements in LLMs, we intend to regularly update this paper by incorporating new sections and featuring the latest LLM models.
The concept of causality plays an important role in human cognition . In the past few decades, causal inference has been well developed in many fields, such as computer science, medicine, economics, and education. With the advancement of deep learning techniques, it has been increasingly used in causal inference against counterfactual data. Typically, deep causal models map the characteristics of covariates to a representation space and then design various objective optimization functions to estimate counterfactual data unbiasedly based on the different optimization methods. This paper focuses on the survey of the deep causal models, and its core contributions are as follows: 1) we provide relevant metrics under multiple treatments and continuous-dose treatment; 2) we incorporate a comprehensive overview of deep causal models from both temporal development and method classification perspectives; 3) we assist a detailed and comprehensive classification and analysis of relevant datasets and source code.
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the substructures of graphs, which are more intuitive and human-intelligible. In this work, we propose a novel method, known as SubgraphX, to explain GNNs by identifying important subgraphs. Given a trained GNN model and an input graph, our SubgraphX explains its predictions by efficiently exploring different subgraphs with Monte Carlo tree search. To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs. To expedite computations, we propose efficient approximation schemes to compute Shapley values for graph data. Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly and directly. Experimental results show that our SubgraphX achieves significantly improved explanations, while keeping computations at a reasonable level.
Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link relies on the convergence of network weights to a smooth function as the number of layers increases. We investigate the properties of weights trained by stochastic gradient descent and their scaling with network depth through detailed numerical experiments. We observe the existence of scaling regimes markedly different from those assumed in neural ODE literature. Depending on certain features of the network architecture, such as the smoothness of the activation function, one may obtain an alternative ODE limit, a stochastic differential equation or neither of these. These findings cast doubts on the validity of the neural ODE model as an adequate asymptotic description of deep ResNets and point to an alternative class of differential equations as a better description of the deep network limit.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191