In this paper, we first extend the result of FL93 and prove universal consistency for a classification rule based on wide and deep ReLU neural networks trained on the logistic loss. Unlike the approach in FL93 that decomposes the estimation and empirical error, we directly analyze the classification risk based on the observation that a realization of a neural network that is wide enough is capable of interpolating an arbitrary number of points. Secondly, we give sufficient conditions for a class of probability measures under which classifiers based on neural networks achieve minimax optimal rates of convergence. Our result is motivated from the practitioner's observation that neural networks are often trained to achieve 0 training error, which is the case for our proposed neural network classifiers. Our proofs hinge on recent developments in empirical risk minimization and on approximation rates of deep ReLU neural networks for various function classes of interest. Applications to classical function spaces of smoothness illustrate the usefulness of our result.
相關內容
Networking：IFIP International Conferences on Networking。
Explanation：國際(ji)網(wang)絡會議。
Publisher：IFIP。
SIT：
In this paper, we investigate the effectiveness of various LLMs in interpreting tabular data through different prompting strategies and data formats. Our analysis extends across six benchmarks for table-related tasks such as question-answering and fact-checking. We introduce for the first time the assessment of LLMs' performance on image-based table representations. Specifically, we compare five text-based and three image-based table representations, demonstrating the influence of representation and prompting on LLM performance. Our study provides insights into the effective use of LLMs on table-related tasks.
In this paper, we present an entropy-stable (ES) discretization using a nodal discontinuous Galerkin (DG) method for the ideal multi-ion magneto-hydrodynamics (MHD) equations. We start by performing a continuous entropy analysis of the ideal multi-ion MHD system, described by, e.g., [Toth (2010) Multi-Ion Magnetohydrodynamics] \cite{Toth2010}, which describes the motion of multi-ion plasmas with independent momentum and energy equations for each ion species. Following the continuous entropy analysis, we propose an algebraic manipulation to the multi-ion MHD system, such that entropy consistency can be transferred from the continuous analysis to its discrete approximation. Moreover, we augment the system of equations with a generalized Lagrange multiplier (GLM) technique to have an additional cleaning mechanism of the magnetic field divergence error. We first derive robust entropy-conservative (EC) fluxes for the alternative formulation of the multi-ion GLM-MHD system that satisfy a Tadmor-type condition and are consistent with existing EC fluxes for single-fluid GLM-MHD equations. Using these numerical two-point fluxes, we construct high-order EC and ES DG discretizations of the ideal multi-ion MHD system using collocated Legendre--Gauss--Lobatto summation-by-parts (SBP) operators. The resulting nodal DG schemes satisfy the second-law of thermodynamics at the semi-discrete level, while maintaining high-order convergence and local node-wise conservation properties. We demonstrate the high-order convergence, and the EC and ES properties of our scheme with numerical validation experiments. Moreover, we demonstrate the importance of the GLM divergence technique and the ES discretization to improve the robustness properties of a DG discretization of the multi-ion MHD system by solving a challenging magnetized Kelvin-Helmholtz instability problem that exhibits MHD turbulence.
In this paper, we propose a new annotation scheme to classify different types of clauses in Terms-and-Conditions contracts with the ultimate goal of supporting legal experts to quickly identify and assess problematic issues in this type of legal documents. To this end, we built a small corpus of Terms-and-Conditions contracts and finalized an annotation scheme of 14 categories, eventually reaching an inter-annotator agreement of 0.92. Then, for 11 of them, we experimented with binary classification tasks using few-shot prompting with a multilingual T5 and two fine-tuned versions of two BERT-based LLMs for Italian. Our experiments showed the feasibility of automatic classification of our categories by reaching accuracies ranging from .79 to .95 on validation tasks.
In this paper, we tackle the problem of computing a sequence of rankings with the guarantee of the Pareto-optimal balance between (1) maximizing the utility of the consumers and (2) minimizing unfairness between producers of the items. Such a multi-objective optimization problem is typically solved using a combination of a scalarization method and linear programming on bi-stochastic matrices, representing the distribution of possible rankings of items. However, the above-mentioned approach relies on Birkhoff-von Neumann (BvN) decomposition, of which the computational complexity is $\mathcal{O}(n^5)$ with $n$ being the number of items, making it impractical for large-scale systems. To address this drawback, we introduce a novel approach to the above problem by using the Expohedron - a permutahedron whose points represent all achievable exposures of items. On the Expohedron, we profile the Pareto curve which captures the trade-off between group fairness and user utility by identifying a finite number of Pareto optimal solutions. We further propose an efficient method by relaxing our optimization problem on the Expohedron's circumscribed $n$-sphere, which significantly improve the running time. Moreover, the approximate Pareto curve is asymptotically close to the real Pareto optimal curve as the number of substantial solutions increases. Our methods are applicable with different ranking merits that are non-decreasing functions of item relevance. The effectiveness of our methods are validated through experiments on both synthetic and real-world datasets.
In this study, we revisit the convergence of AdaGrad with momentum (covering AdaGrad as a special case) on non-convex smooth optimization problems. We consider a general noise model where the noise magnitude is controlled by the function value gap together with the gradient magnitude. This model encompasses a broad range of noises including bounded noise, sub-Gaussian noise, affine variance noise and the expected smoothness, and it has been shown to be more realistic in many practical applications. Our analysis yields a probabilistic convergence rate which, under the general noise, could reach at (\tilde{\mathcal{O}}(1/\sqrt{T})). This rate does not rely on prior knowledge of problem-parameters and could accelerate to (\tilde{\mathcal{O}}(1/T)) where (T) denotes the total number iterations, when the noise parameters related to the function value gap and noise level are sufficiently small. The convergence rate thus matches the lower rate for stochastic first-order methods over non-convex smooth landscape up to logarithm terms [Arjevani et al., 2023]. We further derive a convergence bound for AdaGrad with mometum, considering the generalized smoothness where the local smoothness is controlled by a first-order function of the gradient norm.
In this paper, we investigate the conditions under which link analysis algorithms prevent minority groups from reaching high ranking slots. We find that the most common link-based algorithms using centrality metrics, such as PageRank and HITS, can reproduce and even amplify bias against minority groups in networks. Yet, their behavior differs: one one hand, we empirically show that PageRank mirrors the degree distribution for most of the ranking positions and it can equalize representation of minorities among the top ranked nodes; on the other hand, we find that HITS amplifies pre-existing bias in homophilic networks through a novel theoretical analysis, supported by empirical results. We find the root cause of bias amplification in HITS to be the level of homophily present in the network, modeled through an evolving network model with two communities. We illustrate our theoretical analysis on both synthetic and real datasets and we present directions for future work.
In this paper, we consider robust estimation of claim severity models in insurance, when data are affected by truncation (due to deductibles), censoring (due to policy limits), and scaling (due to coinsurance). In particular, robust estimators based on the methods of trimmed moments (T-estimators) and winsorized moments (W-estimators) are pursued and fully developed. The general definitions of such estimators are formulated and their asymptotic properties are investigated. For illustrative purposes, specific formulas for T- and W-estimators of the tail parameter of a single-parameter Pareto distribution are derived. The practical performance of these estimators is then explored using the well-known Norwegian fire claims data. Our results demonstrate that T- and W-estimators offer a robust and computationally efficient alternative to the likelihood-based inference for models that are affected by deductibles, policy limits, and coinsurance.
In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision. First, we conduct a pilot study based on a 1D signal and relate our findings to 3D scenarios, where the naive joint pose optimization on voxel-based NeRFs can easily lead to sub-optimal solutions. Moreover, based on the analysis of the frequency spectrum, we propose to apply convolutional Gaussian filters on 2D and 3D radiance fields for a coarse-to-fine training schedule that enables joint camera pose optimization. Leveraging the decomposition property in decomposed low-rank tensor, our method achieves an equivalent effect to brute-force 3D convolution with only incurring little computational overhead. To further improve the robustness and stability of joint optimization, we also propose techniques of smoothed 2D supervision, randomly scaled kernel parameters, and edge-guided loss mask. Extensive quantitative and qualitative evaluations demonstrate that our proposed framework achieves superior performance in novel view synthesis as well as rapid convergence for optimization.
In this work, we propose a fast and accurate method to reconstruct activations of classification and semantic segmentation networks by stitching them with a GAN generator utilizing a 1x1 convolution. We test our approach on images of animals from the AFHQ wild dataset, ImageNet1K, and real-world digital pathology scans of stained tissue samples. Our results show comparable performance to established gradient descent methods but with a processing time that is two orders of magnitude faster, making this approach promising for practical applications.
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191