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.
Improves synthetic data for deep model training and adaptation.
This paper improves anomaly detection in lane rendering images for safer navigation.
Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. In this paper, we propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. Our approach considers an existing Monte Ca…
DVAO predicts volumetric ambient occlusion for real-time volume rendering.
The paper uses differentiable rendering to generate semantic counterexamples for improving neural network robustness.
We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" …
ORRB enables fast, customizable rendering of robotics environments.
DSRGAN learns independent structure and rendering without tuple supervision.
Describes rendering scenes in Nil geometry.
Enhances neural rendering with geometry-aware attention.
The idea of computer vision as the Bayesian inverse problem to computer graphics has a long history and an appealing elegance, but it has proved difficult to directly implement. Instead, most vision tasks are approached via complex bottom-up processing pipelines. Here we show that it is possible to write short, simple …
Automates hair color digitization using imaging and deep learning.
A neural scene representation framework enforcing 3D transformations.
We create real-time geodesic rendering for non-isotropic geometries.
ROOTS learns to represent and render 3D scenes with object-centric models.
The common view that our creativity is what makes us uniquely human suggests that incorporating research on human creativity into generative deep learning techniques might be a fruitful avenue for making their outputs more compelling and human-like. Using an original synthesis of Deep Dream-based convolutional neural n…
AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.
The computation of the sparse principal component of a matrix is equivalent to the identification of its principal submatrix with the largest maximum eigenvalue. Finding this optimal submatrix is what renders the problem -hard. In this work, we prove that, if the matrix is positive semidefinite and its …
NeRF-VAE generates 3D scenes with geometric structure from few images.
Automates UI implementation from designer images.
Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according t…
Improves spline quality and accuracy in computational microscopy.
Study examines synthetic images with reflecting materials for training object detectors.
Survey of game theory methods to secure machine learning against adversarial attacks.
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…
Three-dimensional smooth, compact toric varieties (SCTV), when viewed as real six-dimensional manifolds, can admit G-structures rendering them suitable for internal manifolds in supersymmetric flux compactifications. We develop techniques which allow us to systematically construct G-structures on SCTV and read off thei…
We study the problem of robust time series analysis under the standard auto-regressive (AR) time series model in the presence of arbitrary outliers. We devise an efficient hard thresholding based algorithm which can obtain a consistent estimate of the optimal AR model despite a large fraction of the time series points …
Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning. Deep Convolutional Networks (DCNs) have achieved great success in supervised tasks and as such have been widely employed in the semi-supervised learning. In this paper we…
3D adversarial logos can fool object detectors in real-world settings.
A new metric for detecting out-of-distribution samples using neural rendering models.
This study improves scalability of randomized smoothing for certifying classifier robustness.
Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a f…
DocParser parses document structures from renderings like PDFs and scans.
Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the predictions. Currently, the majority of these studies have focused on per…
SketchTransfer task tests deep networks' ability to generalize missing details.
Select-DC reduces GFLOPS for uncertainty estimation in neural networks.
Algorithm finds optimal affine transformation to minimize overall distortion.
In this paper, we consider the numerical pricing of financial derivatives using Radial Basis Function generated Finite Differences in space. Such discretization methods have the advantage of not requiring Cartesian grids. Instead, the nodes can be placed with higher density in areas where there is a need for higher acc…
Learn object dynamics from unlabeled images.
We study a hybrid conditional gradient - smoothing algorithm (HCGS) for solving composite convex optimization problems which contain several terms over a bounded set. Examples of these include regularization problems with several norms as penalties and a norm constraint. HCGS extends conditional gradient methods to cas…
We explore the possibilities of importance sampling in the Monte Carlo pricing of a structured credit derivative referred to as Collateralized Debt Obligation (CDO). Modeling a CDO contract is challenging, since it depends on a pool of (typically about 100) assets, Monte Carlo simulations are often the only feasible ap…
New dynamic backdoor attacks bypass current defenses.
Detects changes in global financial networks before crashes.
This paper proposes and studies a detection technique for adversarial scenarios (dubbed deterministic detection). This technique provides an alternative detection methodology in case the usual stochastic methods are not applicable: this can be because the studied phenomenon does not follow a stochastic sampling scheme,…
Percival uses deep learning to block ads in real-time, minimizing performance impact.
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
Data compression is a popular technique for improving the efficiency of data processing workloads such as SQL queries and more recently, machine learning (ML) with classical batch gradient methods. But the efficacy of such ideas for mini-batch stochastic gradient descent (MGD), arguably the workhorse algorithm of moder…
Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque …