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 spline quality and accuracy in computational microscopy.
Automates hair color digitization using imaging and deep learning.
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…
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a basis in the physical world, such as rotations, translations, changes in lighting…
3D adversarial logos can fool object detectors in real-world settings.
NeRF-VAE generates 3D scenes with geometric structure from few images.
AutoSimulate efficiently optimizes synthetic data generation.
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the effectiveness of several different synthesis techniques and their impact on the complexity o…
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…
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
We generalize stochastic smoothing for gradient estimation of non-differentiable functions.
Pix2Shape learns 3D scene representations from single images without supervision.
Stabilized neural differential equations enforce constraints on dynamical systems.
Describes rendering scenes in Nil geometry.
A neural scene representation framework enforcing 3D transformations.
Differential privacy is a statistical concept that can be explained through hypothesis testing.
We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments. It is based on the Unity3d game engine and interfaces with the MuJoCo physics simulation library. ORRB was designed with visual domain randomization in mind. It is optimized for cloud de…
Newton's method tackles nonlinear mappings into vector bundles with connections and retractions.
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes eve…
We create real-time geodesic rendering for non-isotropic geometries.
Model predicts multi-agent trajectories using a differentiable simulator.
Proposes a model to generate 3D-aware images from 2D images.
Automatically identifies geometric flat outputs for robotic systems.
We analyze the Kozachenko--Leonenko (KL) nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a new minimax lower bound over the Hölder ba…
ROOTS learns to represent and render 3D scenes with object-centric models.
This paper improves anomaly detection in lane rendering images for safer navigation.
A scalable PyTorch framework for non-crossing quantile regression.
AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.
New method reconstructs hidden structures from noisy data.
ProGen improves spatiotemporal forecasting with SDEs and diffusion models.
DVAO predicts volumetric ambient occlusion for real-time volume rendering.
Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previo…
BPQP improves efficiency of differentiable optimization layers for deep learning.
Stella Nera accelerates matrix multiplications with a hash-based approach, achieving high energy efficiency and accuracy.
Paper introduces a modified Allen-Cahn equation for better energy equipartition.
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…
New method finds efficient low-rank neural networks during training.
The aim of this work is to provide fast and accurate approximation schemes for the Monte Carlo pricing of derivatives in LIBOR market models. Standard methods can be applied to solve the stochastic differential equations of the successive LIBOR rates but the methods are generally slow. Our contribution is twofold. Firs…
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…
Graphical models have gained a lot of attention recently as a tool for learning and representing dependencies among variables in multivariate data. Often, domain scientists are looking specifically for differences among the dependency networks of different conditions or populations (e.g. differences between regulatory …
Gradient-free method solves infinite-dimensional optimization problems.
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…
The possible impact of algorithmic recommendation on the autonomy and free choice of Internet users is being increasingly discussed, especially in terms of the rendering of information and the structuring of interactions. This paper aims at reviewing and framing this issue along a double dichotomy. The first one addres…
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" …
Two formulae estimate sensitivity of random vectors to distributional parameters.
Probabilistic numerics expands numerical tasks with black box methods.
We explore a new domain of learning to infer user interface attributes that helps developers automate the process of user interface implementation. Concretely, given an input image created by a designer, we learn to infer its implementation which when rendered, looks visually the same as the input image. To achieve thi…
Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the parameters of any (non-differentiable) simulator, thereby controlling the distribution o…