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 generates cartoon giraffes from few original drawings.
Paper tackles selfie cartoonization with a new GAN.
Paper tackles deep learning's data needs with rule-based augmentation for cartoon coloring.
The New Yorker publishes a weekly captionless cartoon. More than 5,000 readers submit captions for it. The editors select three of them and ask the readers to pick the funniest one. We describe an experiment that compares a dozen automatic methods for selecting the funniest caption. We show that negative sentiment, hum…
Wiatowski and Bölcskei, 2015, proved that deformation stability and vertical translation invariance of deep convolutional neural network-based feature extractors are guaranteed by the network structure per se rather than the specific convolution kernels and non-linearities. While the translation invariance result appli…
A new method for computing image curvature efficiently and accurately.
New concept of k-holes in simple drawings and convex drawings.
Improved ranking method for scarce data with feature info.
VQ-DRAW compresses images and generates realistic samples.
Box Thirding identifies the best arm efficiently under limited samples.
Rotation systems can't always be drawn in surfaces.
We propose a restricted collapsed draw (RCD) sampler, a general Markov chain Monte Carlo sampler of simultaneous draws from a hierarchical Chinese restaurant process (HCRP) with restriction. Models that require simultaneous draws from a hierarchical Dirichlet process with restriction, such as infinite Hidden markov mod…
We present a system for identifying conceptual shifts between visual categories, which will form the basis for a co-creative drawing system to help users draw more creative sketches. The system recognizes human sketches and matches them to structurally similar sketches from categories to which they do not belong. This …
Examines how meridians and parallels help in map drawing.
Criteria found for graph drawings on surfaces.
Study on a bad arm existence checking problem to minimize arm draws.
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of classes. We outline a framework for conditional and unconditional sketch generation, and describe new robust training …
SPX optimizes multiple graph drawing metrics for better readability.
CoSE models complex drawings by treating strokes as a collection that can be composed.
The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular neuropsychological screening tool for cognitive conditions. The Digital Clock Drawing Test (dCDT) uses novel software to analyze data from a digitizing ballpoint pen that reports its position with considerable spatial and temporal precision, making possi…
There are three main thrusts to this article: a new proof of Levi's Enlargement Lemma for pseudoline arrangements in the real projective plane; a new characterization of pseudolinear drawings of the complete graph; and proofs that pseudolinear and convex drawings of have O and O, respect…
This note provides an elementary proof of the folklore fact that draws from a Dirichlet distribution (with parameters less than 1) are typically sparse (most coordinates are small).
Paper finds Dutch Draw optimal baseline for binary classification.
A {\em good drawing\/} of is a drawing of the complete graph with vertices in the sphere such that: no two edges with a common end cross; no two edges cross more than once; and no three edges all cross at the same point. Gioan's Theorem asserts that any two good drawings of that have the same rotations …
We propose an alternative framework to existing setups for controlling false alarms when multiple A/B tests are run over time. This setup arises in many practical applications, e.g. when pharmaceutical companies test new treatment options against control pills for different diseases, or when internet companies test the…
New method learns high-quality Laplacian representations for reinforcement learning.
A new method for spotting symbols in CAD images reduces annotation costs and improves accuracy.
CupNet prunes neural nets for cup-shaped data.
New bounds show limitations of sample-wise information-theoretic generalization.
A new method uses string method to explore diffusion models.
Mathematical analysis shows Delisle-Euler map methods are optimal.
Can certain shapes be drawn with a pencil and eraser?
A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional dist…
Deep convolutional neural networks have led to breakthrough results in numerous practical machine learning tasks such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction …
In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all systems constraints using asynchronous client-server communication and provides attrac…
Examines parallels between human subjects and texts for causal inference.
We usually think of 2-dimensional manifolds as surfaces embedded in Euclidean 3-space. Since humans cannot visualise Euclidean spaces of higher dimensions, it appears to be impossible to give pictorial representations of higher-dimensional manifolds. However, one can in fact encode the topology of a surface in a 1-dime…
SketchTransfer task tests deep networks' ability to generalize missing details.
A grid layout method for graph classification using CNNs.
Paper proves MDS NP-hard and provides a PTAS.
GraphSAC detects anomalies in large graphs by sampling and filtering node subsets.
New bounds on learning algorithm generalization error derived using information density.
Sampling more can make models more confident in wrong answers, not better.
Optimizes tax payments for insurance companies using Lévy risk processes.
We present a simplified exposition of some classical and modern results on graph drawings in the plane. These results are chosen so that they illustrate some spectacular recent higher-dimensional results on the border of topology and combinatorics. We define a mod2-valued self-intersection invariant (i.e. the van Kampe…
Here we draw a handlebody picture for the exotic CP^2 # 2(-CP^2) constructed by Akhmedov and Park.
Here we draw a handlebody picture for the exotic CP^2 # 3(-CP^2), constructed by Akhmedov and Park.
Pulli kolam is a ubiquitous art form in south India. It involves drawing a line looped around a collection of dots (pullis) place on a plane such that three mandatory rules are followed: all line orbits should be closed, all dots are encircled and no two lines can overlap over a finite length. The mathematical foundati…