There has been considerable recent interest in estimating heterogeneous causal effects. In this paper, we introduce conditional average partial causal effects (CAPCE) to reveal the heterogeneity of causal effects with continuous treatment. We provide conditions for identifying CAPCE in an instrumental variable setting. We develop three families of CAPCE estimators: sieve, parametric, and reproducing kernel Hilbert space (RKHS)-based, and analyze their statistical properties. We illustrate the proposed CAPCE estimators on synthetic and real-world data.
相關內容
This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a family of non-stationary solvers that provably subsumes existing numerical ODE solvers and consequently demonstrate considerable improvement in sample approximation (PSNR) over these baselines. Compared to model distillation, BNS solvers benefit from a tiny parameter space ($<$200 parameters), fast optimization (two orders of magnitude faster), maintain diversity of samples, and in contrast to previous solver distillation approaches nearly close the gap from standard distillation methods such as Progressive Distillation in the low-medium NFE regime. For example, BNS solver achieves 45 PSNR / 1.76 FID using 16 NFE in class-conditional ImageNet-64. We experimented with BNS solvers for conditional image generation, text-to-image generation, and text-2-audio generation showing significant improvement in sample approximation (PSNR) in all.
In this paper, we introduce a set representation called polynomial logical zonotopes for performing exact and computationally efficient reachability analysis on logical systems. Polynomial logical zonotopes are a generalization of logical zonotopes, which are able to represent up to 2^n binary vectors using only n generators. Due to their construction, logical zonotopes are only able to support exact computations of some logical operations (XOR, NOT, XNOR), while other operations (AND, NAND, OR, NOR) result in over-approximations in the reduced space, i.e., generator space. In order to perform all fundamental logical operations exactly, we formulate a generalization of logical zonotopes that is constructed by dependent generators and exponent matrices. We prove that through this polynomial-like construction, we are able to perform all of the fundamental logical operations (XOR, NOT, XNOR, AND, NAND, OR, NOR) exactly in the generator space. While we are able to perform all of the logical operations exactly, this comes with a slight increase in computational complexity compared to logical zonotopes. We show that we can use polynomial logical zonotopes to perform exact reachability analysis while retaining a low computational complexity. To illustrate and showcase the computational benefits of polynomial logical zonotopes, we present the results of performing reachability analysis on two use cases: (1) safety verification of an intersection crossing protocol and (2) reachability analysis on a high-dimensional Boolean function. Moreover, to highlight the extensibility of logical zonotopes, we include an additional use case where we perform a computationally tractable exhaustive search for the key of a linear feedback shift register.
Recent advances in LLMs have sparked a debate on whether they understand text. In this position paper, we argue that opponents in this debate hold different definitions for understanding, and particularly differ in their view on the role of consciousness. To substantiate this claim, we propose a thought experiment involving an open-source chatbot $Z$ which excels on every possible benchmark, seemingly without subjective experience. We ask whether $Z$ is capable of understanding, and show that different schools of thought within seminal AI research seem to answer this question differently, uncovering their terminological disagreement. Moving forward, we propose two distinct working definitions for understanding which explicitly acknowledge the question of consciousness, and draw connections with a rich literature in philosophy, psychology and neuroscience.
Technological innovation plays a crucial role in driving economic growth and development. In this study, we investigate the extent to which technological innovation contributes to a more sustainable future and fosters entrepreneurship. To examine this, we focus on robotic process automation (RPA) highly relevant technology. We conducted a comprehensive analysis by examining the usage of RPA and its impact on environmental, social, and governance (ESG) factors. Our research involved gathering data from the 300 largest companies in terms of market capitalization. We assessed whether these companies used RPA and obtained their corresponding ESG ratings. To investigate the relationship between RPA and ESG, we employed a contingency table analysis, which involved categorizing the data based on ESG ratings. We further used Pearson's Chi-square Test of Independence to assess the impact of RPA on ESG. Our findings revealed a statistically significant association between RPA and ESG ratings, indicating their interconnection. The calculated value for Pearson's Chi-square Test of Independence was 6.54, with a corresponding p-value of 0.0381. This indicates that at a significance level of five percent, the RPA and ESG variables depend on each other. These results suggest that RPA, representative of modern technologies, likely influences the achievement of a sustainable future and the promotion of entrepreneurship. In conclusion, our study provides empirical evidence supporting the notion that technological innovations such as RPA have the potential to positively shape sustainability efforts and entrepreneurial endeavours.
In this paper, we propose a deep learning based model for Acoustic Anomaly Detection of Machines, the task for detecting abnormal machines by analysing the machine sound. By conducting extensive experiments, we indicate that multiple techniques of pseudo audios, audio segment, data augmentation, Mahalanobis distance, and narrow frequency bands, which mainly focus on feature engineering, are effective to enhance the system performance. Among the evaluating techniques, the narrow frequency bands presents a significant impact. Indeed, our proposed model, which focuses on the narrow frequency bands, outperforms the DCASE baseline on the benchmark dataset of DCASE 2022 Task 2 Development set. The important role of the narrow frequency bands indicated in this paper inspires the research community on the task of Acoustic Anomaly Detection of Machines to further investigate and propose novel network architectures focusing on the frequency bands.
In this paper, we consider the generation and utilization of helper data for physical unclonable functions (PUFs) that provide real-valued readout symbols. Compared to classical binary PUFs, more entropy can be extracted from each basic building block (PUF node), resulting in longer keys/fingerprints and/or a higher reliability. To this end, a coded modulation and signal shaping scheme that matches the (approximately) Gaussian distribution of the readout has to be employed. A new helper data scheme is proposed that works with any type of coded modulation/shaping scheme. Compared to the permutation scheme from the literature, less amount of helper data has to be generated and a higher reliability is achieved. Moreover, the recently proposed idea of a two-metric helper data scheme is generalized to coded modulation and a general S-metric scheme. It is shown how extra helper data can be generated to improve decodability. The proposed schemes are assessed by numerical simulations and by evaluation of measurement data. We compare multi-level codes using a new rate design strategy with bit-interleaved coded modulation and trellis shaping with a distribution matcher. By selecting a suitable design, the rate per PUF node that can be reliably extracted can be as high as 2~bit/node.
In this paper, we propose an adaptive approach, based on mesh refinement or parametric enrichment with polynomial degree adaption, for numerical solution of convection dominated equations with random input data. A parametric system emerged from an application of stochastic Galerkin approach is discretized by using a symmetric interior penalty Galerkin (SIPG) method with upwinding for the convection term in the spatial domain. We derive a residual-based error estimator contributed by the error due to the SIPG discretization, the (generalized) polynomial chaos discretization in the stochastic space, and data oscillations. Then, the reliability of the proposed error estimator, an upper bound for the energy error up to a multiplicative constant, is shown. Moreover, to balance the errors stemmed from spatial and stochastic spaces, the truncation error coming from Karhunen--Lo\`{e}ve expansion is also considered in the numerical simulations. Last, several benchmark examples including a random diffusivity parameter, a random velocity parameter, random diffusivity/velocity parameters, and a random (jump) discontinuous diffusivity parameter, are tested to illustrate the performance of the proposed estimator.
In this paper, we explore the intriguing similarities between the structure of a discrete neural network, such as a spiking network, and the composition of a piano piece. While both involve nodes or notes that are activated sequentially or in parallel, the latter benefits from the rich body of music theory to guide meaningful combinations. We propose a novel approach that leverages musical grammar to regulate activations in a spiking neural network, allowing for the representation of symbols as attractors. By applying rules for chord progressions from music theory, we demonstrate how certain activations naturally follow others, akin to the concept of attraction. Furthermore, we introduce the concept of modulating keys to navigate different basins of attraction within the network. Ultimately, we show that the map of concepts in our model is structured by the musical circle of fifths, highlighting the potential for leveraging music theory principles in deep learning algorithms.
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.
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191