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.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
This paper analyzes the variability of Concept Activation Vectors (CAVs).
RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.
In this paper we study a symmetry group of vector space. Basis manifold is a homogeneous space of a symmetry group. This concept leads us to the definition of active and passive transformations on basis manifold. Active transformation can be expressed as a transformation of vector space. Passive transformation gives ab…
Unified framework for testing deep learning models with concept activation vectors.
Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in th…
Deep learning skin lesion classifier explained using CAVs.
Researchers apply concept-based explainability to EEG data.
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), whic…
New neural operators learn structured patterns efficiently.
Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate layers by quantifying its ability to distinguish a user-defined concept (from r…
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing. The methodology has been demonstrated to improve the performance of MLC algorithms whe…
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated w…
Framework models supervised learning in non-stationary data.
Active management is a term that has many meanings and we have found the defining characteristics needed for success as an "active manager" elusive within the literature. In this paper we offer a set of criteria that defines an active manager and his success. In order to facilitate this, we introduce several definition…
MCD offers a complete model understanding for high-stake decisions.
Abstract framework for no-arbitrage concepts in topological vector lattices.
New method uses weighting vectors for efficient boundary and outlier detection.
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
DeepStreamCE detects new classes in streaming deep neural networks.
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active…
FedMAX tackles activation divergence in FL, improving accuracy and efficiency.
DORA analyzes deep neural networks' internal representations to detect spurious correlations.
Traditional energy-based learning models associate a single energy metric to each configuration of variables involved in the underlying optimization process. Such models associate the lowest energy state to the optimal configuration of variables under consideration, and are thus inherently dissipative. In this paper we…
We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…
The aim of the present paper is to investigate intrinsically the notion of a concircular -vector field in Finsler geometry. This generalizes the concept of a concircular vector field in Riemannian geometry and the concept of a concurrent vector field in Finsler geometry. Some properties of concircular -vector fie…
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…
Most neural network designs for FPGAs are inflexible. In this paper, we propose a flexible VHDL structure that would allow any neural network to be implemented on multiple FPGAs. Moreover, the VHDL structure allows for testing as well as training multiple neural networks. The VHDL design consists of multiple processor …
The paper proposes methods to find a shared active subspace for multivariate vector-valued functions.
Study uses neural networks to improve option pricing accuracy.
Universal approximation for ODENet and ResNet with a single activation function.
To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good p…
Analogously to the concept of a curvature of curve and surface, in the differential geometry, in the main part of this paper the concept of the curvature of the hyper-dimensional vector spaces of Riemannian metric is generally defined. The defined concept of the curvature of Riemannian spaces of higher dimensions M: M>…
A framework monitors and diagnoses concept drift in supervised learning models.
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…
The goal of this article is to describe the concepts of system dynamics and its applications to the simulation modeling of financial institutions daily activity. The hybrid method of the re-engineering of banking business processes based upon combination of system dynamics, queuing theory and tools of ordinary differen…
Unified Bayesian model explains in-context learning and activation steering in LLMs.
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for building effective data-driven solutions. We develop an active learning framework for mining such relations subject to a strict order. Our a…
BALLAST optimizes Lagrangian observer placement for ocean vector fields.
This research integrates attention into XAI frameworks for better model explanations.
VICE embeds concepts in a vector space using human data.
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically labels the majority of the datapoints, thus drastically reducing the human labeling b…
We study covariance matrix estimation for the case of partially observed random vectors, where different samples contain different subsets of vector coordinates. Each observation is the product of the variable of interest with a Bernoulli random variable. We analyze an unbiased covariance estimator under this mod…
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning. While saliency maps may help identify relevant features (e.g., p…
Paper revises power theory using classical mechanics concepts.
On the basis of Liouville theorem the generalization of the Nambu mechanics is considered. For three-dimensional phase space the concept of vector hamiltonian and vector lagrangian is entered.