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.
New model of vague knowledge without strict partitions or transitivity.
Analysts use vague language in reports to convey useful information about future payoffs.
Adversarial meta-learning computes Gamma-minimax estimators for vague prior knowledge.
We discuss fun problems, vaguely related to notions and theorems of a course in differential geometry. This paper can be regarded as a weekend "treasure chest" supplementing the course weekday lecture notes. The problems and solutions are not original, while their relation to the course might be so.
New method samples Jeffreys prior for objective Bayesian inference.
We have developed an efficient algorithm for the maximum likelihood joint tracking and association problem in a strong clutter for GMTI data. By using an iterative procedure of the dynamic logic process "from vague-to-crisp," the new tracker overcomes combinatorial complexity of tracking in highly-cluttered scenarios a…
We shall prove that under some volume growth condition, the essential spectrum of the Laplacian contains the interval if an -dimensional Riemannian manifold has an end and the average of the part of the Ricci curvature on the end which lies below a nonpositive constant converges to ze…
A dictionary connects symplectic to contact geometry, with applications to complex and G-structures.
Random hyperbolic 3-manifolds can be obtained via Dehn surgery.
Study shows HFT benefits large traders under certain conditions.
In shape analysis, the concept of shape spaces has always been vague, requiring a case-by-case approach for every new type of shape. In this paper, we give a general definition for an abstract space of shapes in a manifold. This notion encompasses every shape space studied so far in the literature, and offers a rigorou…
Review of priors in Bayesian deep learning models.
The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic abilit…
Deep neural networks (DNNs) are known as black-box models. In other words, it is difficult to interpret the internal state of the model. Improving the interpretability of DNNs is one of the hot research topics. However, at present, the definition of interpretability for DNNs is vague, and the question of what is a high…
QLSTM outperforms LSTM in predicting KSE 100 index movements.
Unified framework for intersectionally fair AI models using MIO.
In an earlier paper we introduced rectangular diagrams of surfaces and showed that any isotopy class of a surface in the three-sphere can be presented by a rectangular diagram. Here we study transformations of those diagrams and introduce moves that allow transition between diagrams representing isotopic surfaces. We a…
In this paper, we derive a Bayesian model order selection rule by using the exponentially embedded family method, termed Bayesian EEF. Unlike many other Bayesian model selection methods, the Bayesian EEF can use vague proper priors and improper noninformative priors to be objective in the elicitation of parameter prior…
The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which are typically underspecified by the data, and can represent many compelling but d…
If NAS methods are solutions, what is the problem? Most existing NAS methods require two-stage parameter optimization. However, performance of the same architecture in the two stages correlates poorly. In this work, we propose a new problem definition for NAS, task-specific end-to-end, based on this observation. We arg…
Convolutional neural networks (CNNs) in recent years have made a dramatic impact in science, technology and industry, yet the theoretical mechanism of CNN architecture design remains surprisingly vague. The CNN neurons, including its distinctive element, convolutional filters, are known to be learnable features, yet th…
A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with complex-valued vectors followed by (2) taking the absolute value of every entry…
For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients, though even this guideline has remained relatively vague and circumstantial. We …
New framework shows ERM is optimal for both interpolation and extrapolation in domain generalization.
Study finds no significant difference in neural network weights with quantum random numbers.
Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior. As the minimization can only be carried out approximately, this approximation i…
Recent advances in deep pose estimation models have proven to be effective in a wide range of applications such as health monitoring, sports, animations, and robotics. However, pose estimation models fail to generalize when facing images acquired from in-bed pressure sensing systems. In this paper, we address this chal…
The paper tackles model collapse in GPLVMs by improving kernel flexibility and projection variance.
Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) and natural language more suitable to describe vague concepts and ideas…
In this paper we use fuzzy systems theory to convert the technical trading rules commonly used by stock practitioners into excess demand functions which are then used to drive the price dynamics. The technical trading rules are recorded in natural languages where fuzzy words and vague expressions abound. In Part I of t…
Review of uncertainty representation methods in risk management.
We introduce a simple combinatorial way, which we call a rectangular diagram of a surface, to represent a surface in the three-sphere. It has a particularly nice relation to the standard contact structure on and to rectangular diagrams of links. By using rectangular diagrams of surfaces we are going, in p…
Paper proves convergence of warped product manifolds to a nonnegative scalar curvature limit.
Paper studies identifiability and stability of drifting fields in generative modeling.
Fuzzy clustering with similarity queries improves efficiency and accuracy.
The paper explores identifiability and stability in drifting fields using companion-elliptic kernels.
For non-smooth surfaces, the measure of Brownian loops is derived using the Polyakov-Alvarez formula.
Proposes using prior variable importance information in high-dimensional regression.
TadGAN detects anomalies in time series data using GANs and LSTM.
Recent student knowledge modeling algorithms such as Deep Knowledge Tracing (DKT) and Dynamic Key-Value Memory Networks (DKVMN) have been shown to produce accurate predictions of problem correctness within the same learning system. However, these algorithms do not attempt to directly infer student knowledge. In this pa…
A new framework for knowledge graph embedding using sheaves.
Framework evaluates the impact of prior knowledge in deep learning models.
It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation learning by removing noisy features or samples, complementing incomplete data, a…
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from…
Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion). In many cases, insufficient external resources in the knowledge population hinde…
This paper enhances language models with knowledge awareness.
Survey of methods to incorporate external knowledge into stock price prediction.
New model enables AI to learn autonomously.