A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Develops algorithms to optimize machine replacement schedules using operational data.
CGRL improves graph neural networks' OOD generalization by blocking spurious correlations.
Softmax is found ineffective for NL block, leading to improved performance.
Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks,…
The desire to map neural networks to varying-capacity devices has led to the development of a wealth of compression techniques, many of which involve replacing standard convolutional blocks in a large network with cheap alternative blocks. However, not all blocks are created equally; for a required compute budget there…
This paper introduces GLT for better input data representation in BNN and proposes a compact topology with block pruning.
Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its deployment to situations with light computing resources. Researchers resort to the re…
Training-free looped transformers improve model performance without additional training.
K-bMOM robustly clusters data with outliers, improving on Lloyd-type methods.
The study extends stochastic block models to geometric settings, focusing on community detection and information flow.
Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.
Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why L…
The study examines MCMC methods for arbitrary objectives and finds likelihood sharpness impacts performance and regularization.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
Tiled Squeeze-and-Excite improves channel attention with local spatial context.
In this paper we present a kinetic model with stochastic game-type interactions, analyzing the relationship between the level of political competition in a society and the degree of economic liberalization. The above issue regards the complex interactions between economy and institutional policies intended to introduce…
This paper extends Median-of-Means to new learning problems involving pairwise comparisons.
This paper optimizes subsampling for large datasets using Poisson distribution.
New method improves scalability of SGD for large datasets.
The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing datacenter operators to adopt domain-specific accelerators to train them. These accelerators typically employ densely packed full precision floating-point arithmetic to maximize performance per area. Ongoing research efforts seek t…
New ARIMA framework improves forecast accuracy for economic and financial time series.
DAM with MRL improves relational reasoning in MANNs.
The one-term distributive homology was introduced by J.H.Przytycki as an atomic replacement of rack and quandle homology, which was first introduced and developed by R.Fenn, C.Rourke and B.Sanderson, and J.S.Carter, S.Kamada and M.Saito. This homology was initially suspected to be torsion-free, but we show in this pape…
The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by generative adversarial networks, or GANs). In this work, we study the algorithmic aspects of such a learning-based approach from a theor…
Recent trends of incorporating attention mechanisms in vision have led researchers to reconsider the supremacy of convolutional layers as a primary building block. Beyond helping CNNs to handle long-range dependencies, Ramachandran et al. (2019) showed that attention can completely replace convolution and achieve state…
Improved tensor GLM estimation for complex data.
Paper proves SHB convergence with biased gradients and approximate step sizes.
Continuous-depth Evoformer reduces protein folding prediction time and resource usage.
The paper classifies certain singular projective varieties with specific properties.
We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems. We propose to use machine learning automatic differentiation libraries to develop hybrid numerical models that combine components based on prior physical knowledge with components based on neural networks. In these…
We propose ROI regularization (ROIreg) as a semi-supervised learning method for image classification. ROIreg focuses on the maximum probability of a posterior probability distribution g(x) obtained when inputting an unlabeled data sample x into a convolutional neural network (CNN). ROIreg divides the pixel set of x int…
SGPA calibrates transformer uncertainty for safety-critical tasks.
This paper presents a novel Block Iterative Bayesian Algorithm (Block-IBA) for reconstructing block-sparse signals with unknown block structures. Unlike the existing algorithms for block sparse signal recovery which assume the cluster structure of the nonzero elements of the unknown signal to be independent and identic…
This letter presents a novel Block Bayesian Hypothesis Testing Algorithm (Block-BHTA) for reconstructing block sparse signals with unknown block structures. The Block-BHTA comprises the detection and recovery of the supports, and the estimation of the amplitudes of the block sparse signal. The support detection and rec…
Proposes a Nested Block Model to unify various network block models.
We examine the recovery of block sparse signals and extend the framework in two important directions; one by exploiting signals' intra-block correlation and the other by generalizing signals' block structure. We propose two families of algorithms based on the framework of block sparse Bayesian learning (BSBL). One fami…
K-means clustering improved for robustness to outliers and distribution shifts.
We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1 regularization (inducing sparse kernel combination), block-l2 regularization (inducing un…
This work tackles representation learning by introducing stochastic competition-based activations.
SympFormer accelerates attention blocks using inertial dynamics on density spaces.
New kernel models multi-output Gaussian processes accurately.
We introduce block-tree graphs as a framework for deriving efficient algorithms on graphical models. We define block-tree graphs as a tree-structured graph where each node is a cluster of nodes such that the clusters in the graph are disjoint. This differs from junction-trees, where two clusters connected by an edge al…
We simplify matrix computations for block matrices, especially useful for covariance and correlation matrices.
Attention mechanism is a hot spot in deep learning field. Using channel attention model is an effective method for improving the performance of the convolutional neural network. Squeeze-and-Excitation block takes advantage of the channel dependence, selectively emphasizing the important channels and compressing the rel…
Proposes BMME for optimizing nonsmooth nonconvex problems with block structure.
Alternating Direction Method of Multipliers (ADMM) has become a widely used optimization method for convex problems, particularly in the context of data mining in which large optimization problems are often encountered. ADMM has several desirable properties, including the ability to decompose large problems into smalle…
Paper proposes ABDR for convex subspace clustering with adaptive block diagonal representation.
New activation networks improve model efficiency and performance.