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.
Paper examines how adversarial ML attacks and defenses impact civil liberties and human rights.
This paper presents thirteen datasets for binary, multiclass and multilabel classification based on the European Court of Human Rights judgments since its creation. The interest of such datasets is explained through the prism of the researcher, the data scientist, the citizen and the legal practitioner. Contrarily to m…
In this study, machine learning models were constructed to predict whether judgments made by the European Court of Human Rights (ECHR) would lead to a violation of an Article in the Convention on Human Rights. The problem is framed as a binary classification task where a judgment can lead to a "violation" or "non-viola…
This article reviews entity resolution methods and their applications.
Designing AI market for content creation
AI beats 95% of humans in Rock-Paper-Scissors.
A new algorithm improves recommendation systems by considering repeated exposure to actions.
Artificial Intelligence (AI) has become an integral part of domains such as security, finance, healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human terms is a key challenge--due to the high complexity of the model, as well as the potential implications on human interests, rights, …
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies. Reliability measures how likely a subject will respond to a question seriously; and regularity measures how often a human will agree with other seriously-entered responses coming…
Proposes HEX for human-in-the-loop explainability in ML models.
Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturally…
A novel method predicts shape development using Riemannian shape spaces.
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to per…
We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perp…
As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assura…
Human activity recognition plays an important role in people's daily life. However, it is often expensive and time-consuming to acquire sufficient labeled activity data. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labe…
Efficient usage of the knowledge provided by the Linked Data community is often hindered by the need for domain experts to formulate the right SPARQL queries to answer questions. For new questions they have to decide which datasets are suitable and in which terminology and modelling style to phrase the SPARQL query. In…
People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately. Many techniques have been devised …
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is trained with rewards provided by a discriminator network simultaneously trained to assess the realism of the agent's samples, either uncond…
Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be use…
Missing data has a ubiquitous presence in real-life applications of machine learning techniques. Imputation methods are algorithms conceived for restoring missing values in the data, based on other entries in the database. The choice of the imputation method has an influence on the performance of the machine learning t…
Background: Cardiac MRI derived biventricular mass and function parameters, such as end-systolic volume (ESV), end-diastolic volume (EDV), ejection fraction (EF), stroke volume (SV), and ventricular mass (VM) are clinically well established. Image segmentation can be challenging and time-consuming, due to the complex a…
Paper proposes an ensemble approach to improve fairness in classifier decisions.
We report the first, to the best of our knowledge, hand-in-hand collaboration between human rights activists and machine learners, leveraging crowd-sourcing to study online abuse against women on Twitter. On a technical front, we carefully curate an unbiased yet low-variance dataset of labeled tweets, analyze it to acc…
In this paper, mm-Pose, a novel approach to detect and track human skeletons in real-time using an mmWave radar, is proposed. To the best of the authors' knowledge, this is the first method to detect >15 distinct skeletal joints using mmWave radar reflection signals. The proposed method would find several applications …
Self-play fine-tuning improves diffusion models for text-to-image generation.
HighRes-net enhances satellite imagery by fusing multiple low-res views.
Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have s…
We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture. In our solution, each video frame is corrected for perspective using projective tra…
Generating music has a few notable differences from generating images and videos. First, music is an art of time, necessitating a temporal model. Second, music is usually composed of multiple instruments/tracks with their own temporal dynamics, but collectively they unfold over time interdependently. Lastly, musical no…
Both scientists and children make important structural discoveries, yet their computational underpinnings are not well understood. Structure discovery has previously been formalized as probabilistic inference about the right structural form --- where form could be a tree, ring, chain, grid, etc. [Kemp & Tenenbaum (2008…
Linear ODEs are solved by geodesics in hyperbolic geometry.
New framework for contesting algorithmic decisions, not just explaining them.
The paper revisits the -Yamabe problem and proves the existence of a conformal metric with constant -scalar curvature.
Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning
The paper proves foliations of solutions to the minimal surface equation in exterior domains.
The paper examines differentiability of horizons along their generators in Lorentz manifolds.
Uniqueness of quasi-roots explored in right-angled Artin groups.
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data subset selection and active learning techniques have been proposed as possible s…
Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and consequently trusting th…
A new matrix concentration inequality for random products of matrices.
For a Lie group and a vector bundle we study those actions of the Lie group on for which the action map is a morphism of vector bundles, and call those \emph{affine actions}. We prove that the category of such actions over a fixed …
Prob2Vec embeds problems for adaptive tutoring, achieving high similarity accuracy.
Detects right-veering properties in open books using combinatorial methods.
Surveying connections between graph combinatorics and algebraic right-angled Artin groups.
We introduce a notion of "quasi-right-veering" for closed braids, which plays an analogous role to "right-veering" for open books. We show that a transverse link in a contact 3-manifold is non-loose if and only if every braid representative of with respect to every open book decomposition that supports …
The study characterizes spacetime and modified gravity models using projective curvature tensor.
In this paper we study the right-angled Coxeter groups that acts geometrically on the Salvetti complex of a certain right-angled Artin group, which we refer to as Croke-Kleiner spaces. We prove that any right-angled Coxeter group that acts geometrically on the Croke-Kleiner spaces acts with angles between reflect…