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.
The paper extends statistical inference methods for black-box generative models.
Improves model classification accuracy in black-box settings.
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the negative log-likelihood of the model at each iteration and updates to the minimizer of this upper-bound. We first provide a "model level" in…
XGNN explains graph neural networks by generating graphs that maximize model predictions.
Interpreting machine learning models helps understand adversarial attacks and defenses.
We propose a multifractal model for short-term interest rates. The model is a version of the Markov-Switching Multifractal (MSM), which incorporates the well-known level effect observed in interest rates. Unlike previously suggested models, the level-MSM model captures the power-law scaling of the structure functions a…
A framework evaluates the impact of different modules in graph contrastive learning.
Complex black-box predictive models may have high accuracy, but opacity causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, interpretable models require more work related to feature engineering, which is very time consuming. Can we train interpretable and accurate mod…
Unified framework LPCD optimizes quantization of complex submodules.
Generative model learns conditional distributions on collective variable levels.
LLMs excel at summarizing and repairing complex models without needing full models.
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones. To alleviate this issue, it has been proposed to keep around a…
Bayesian data selection framework ensures fairness in machine learning models.
In line with the recent research and debates about econophysics and financial economics, this article discusses on usual misunderstandings between the two disciplines in terms of modelling and basic hypotheses. In the literature devoted to econophysics, the methodology used by financial economists is frequently conside…
Ensemble models provide more accurate feature importance estimates than single models.
Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an orthogonal direction: how to conduct more energy-efficient training of CNNs, so as to enable on-de…
We present a robust alternative to principal component analysis (PCA) --- called elliptical component analysis (ECA) --- for analyzing high dimensional, elliptically distributed data. ECA estimates the eigenspace of the covariance matrix of the elliptical data. To cope with heavy-tailed elliptical distributions, a mult…
This paper presents a novel CNN-RNN based approach, which exploits multiple CNN features for dimensional emotion recognition in-the-wild, utilizing the One-Minute Gradual-Emotion (OMG-Emotion) dataset. Our approach includes first pre-training with the relevant and large in size, Aff-Wild and Aff-Wild2 emotion databases…
XPER methodology decomposes credit scoring model performance.
While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power. A naive approach to resolve this on the model level is to use simp…
As relational datasets modeled as graphs keep increasing in size and their data-acquisition is permeated by uncertainty, graph-based analysis techniques can become computationally and conceptually challenging. In particular, node centrality measures rely on the assumption that the graph is perfectly known -- a premise …
A new framework for robustness analysis of deep neural networks using PAC-model learning.
In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In cont…
This paper enhances the Random Survival Forest model for better predictive maintenance.
This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM…
Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML's impressive performance in commercial applications, several unique challenges exist …
Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal models of the users states (e.g., engagement) are therefore needed. Most of the existing works that try t…
The rapid growth of data size and accessibility in recent years has instigated a shift of philosophy in algorithm design for artificial intelligence. Instead of engineering algorithms by hand, the ability to learn composable systems automatically from massive amounts of data has led to ground-breaking performance in im…
GCNs favor high-degree nodes, leading to biased performance; a new method mitigates this.
New representation theory for closed geodesic subflows.
Proves EGF representations in specific geometric contexts.
The paper establishes isomorphisms and constructs colored versions of Lawrence representations.
Study k-positive surface group representations and their degenerations.
Develops theory of Anosov representations for Fuchsian groups, showing stability and analytical properties.
New representations defined for groups and graphs, with applications to stable representations.
Collar lemma proven for certain surface group representations.
Study subgroup actions on mapping class groups using Heisenberg representations.
Researchers describe unitary representations of mixed braid groups.
This paper addresses law invariant coherent risk measures and their Kusuoka representations. By elaborating the existence of a minimal representation we show that every Kusuoka representation can be reduced to its minimal representation. Uniqueness -- in a sense specified in the paper -- of the risk measure's Kusuoka r…
A very popular problem on braid groups has recently been solved by Bigelow and Krammer, namely, they have found a faithful linear representation for the braid group B_n. In their papers, Bigelow and Krammer suggested that their representation is the monodromy representation of a certain fibration. Our goal in this pape…
Let S be a closed orientable surface of genus at least 2 and let G be a semisimple real algebraic group of non-compact type. We consider a class of representations from the fundamental group of S to G called positively ratioed representations. These are Anosov representations with the additional condition that certain …
In this paper, we introduce a study of prolongations of representations of Lie groups. We obtain a faithful (one-to-one) representation of TG where G is a finite-dimensional Lie group and TG is the tangent bundle of G, by using (not necessarily faithful) representations of G. We show that tangent functions of Lie group…
Polynomial representations found in surface braid and mapping class groups.
Paper addresses the disparity between sampled and mean representations in disentangled learning.
New -positive representations of surface groups discovered.
New representations for surface groups expand known Anosov classes.
New findings on cusped Borel Anosov representations and their properties.