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.
A new data-level recombination strategy improves RGB-D salient object detection.
Study reveals how Fisher information changes with network depth, finding it grows linearly.
Extends partitioned local depth concept with probabilistic considerations.
We study the behavior of untrained neural networks whose weights and biases are randomly distributed using mean field theory. We show the existence of depth scales that naturally limit the maximum depth of signal propagation through these random networks. Our main practical result is to show that random networks may be…
Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.
Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between adjacent inputs. However, the approaches often use a fixed depth, which is at the …
We describe a method to infer dense depth from camera motion and sparse depth as estimated using a visual-inertial odometry system. Unlike other scenarios using point clouds from lidar or structured light sensors, we have few hundreds to few thousand points, insufficient to inform the topology of the scene. Our method …
Paper proves depth bounds for taut foliations using instanton Floer homology.
Framework benchmarks optimizers on multiple criteria.
Generative model separates objects, positions, and appearances in images.
In this paper, we present a framework to control a self-driving car by fusing raw information from RGB images and depth maps. A deep neural network architecture is used for mapping the vision and depth information, respectively, to steering commands. This fusion of information from two sensor sources allows to provide …
Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models are structured with a transition depth of 2-4 layers. Recurrent Highway Networks …
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better cla…
Recent work in signal propagation theory has shown that dropout limits the depth to which information can propagate through a neural network. In this paper, we investigate the effect of initialisation on training speed and generalisation for ReLU networks within this depth limit. We ask the following research question:…
In this paper, we present a multi-period trading model in the style of Kyle (1985)'s inside trading model, by assuming that there are at least two insiders in the market with long-lived private information, under the requirement that each insider publicly discloses his stock trades after the fact. Based on this model, …
Study explores how dataset breadth and depth affect Siamese Neural Network performance.
MPNNs over-squash distant node information, study shows.
Our study analyzes how neural network initialization affects privacy and utility in overparameterized models.
This paper introduces depth functions for ranking data, improving statistical summaries.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
Study reveals how depth of reasoning affects generalization in models.
Graphs avoid oversmoothing with properly initialized weights.
Understanding the representational power of Deep Neural Networks (DNNs) and how their structural properties (e.g., depth, width, type of activation unit) affect the functions they can compute, has been an important yet challenging question in deep learning and approximation theory. In a seminal paper, Telgarsky highlig…
Deep RNNs excel at capturing long-term dependencies in sequential data.
Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks. This requires considerable efforts, from the scientific community, to find new algorithms that solve computer vision problems, such as object recognition. The diffusion of RGB-D cameras directed the stu…
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not poss…
In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the global minimum value of corresponding classical machine-learning models, and are gu…
Study shows marketable order routing to wholesalers benefits all traders, leading to lower market depth and price volatility.
The paper develops a method to create robust control policies for robots using information bottlenecks.
Expressivity is one of the most significant issues in assessing neural networks. In this paper, we provide a quantitative analysis of the expressivity for the deep neural network (DNN) from its dynamic model, where the Hilbert space is employed to analyze the convergence and criticality. We study the feature mapping of…
Price impact of a trade is an important element in pre-trade and post-trade analyses. We introduce a framework to analyze the market price of liquidity risk, which allows us to derive an inhomogeneous Bernoulli ordinary differential equation. We obtain two closed form solutions, one of which reproduces the linear funct…
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous localization and mapping (SLAM), path planning and navigation, require some form of 3D sp…
Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this paper, we propose two novel network quantization approaches, single-level network qu…
This is the third of three papers that refine and extend portions of our earlier preprint, "The depth of a knot tunnel." Together, they rework the entire preprint. In this paper, we use the theory of tunnel number 1 knots that we introduced in "The tree of knot tunnels" to strengthen the Tunnel Leveling Theorem of H. G…
Regression Trees analyze stock returns, revealing market excess return as the most informative factor.
A new depth measure for non-convex data supports, faster than halfspace depth.
In recent years it has become popular to study machine learning problems in a setting of ordinal distance information rather than numerical distance measurements. By ordinal distance information we refer to binary answers to distance comparisons such as . For many problems in machine learning and statist…
The paper studies randomized approximations of Tukey's depth for log-concave isotropic data.
Proposes a new information-theoretic framework for analyzing deep neural networks.
This paper connects functional data analysis with machine learning techniques.
Measures difficulty of predictions to improve deep learning models.
Convolutional neural networks (CNN) are generally designed with a heuristic initialization of network architecture and trained for a certain task. This often leads to overparametrization after learning and induces redundancy in the information flow paths within the network. This robustness and reliability is at the inc…
This study uses deep learning to analyze stock market sentiment from financial forums.
A new depth measure based on optimal control theory captures multi-modal data.
Multidimensional recurrent neural networks (MDRNNs) have shown a remarkable performance in the area of speech and handwriting recognition. The performance of an MDRNN is improved by further increasing its depth, and the difficulty of learning the deeper network is overcome by using Hessian-free (HF) optimization. Given…
A new depth measure and median defined on Hadamard manifolds.
New approach uses loss functions to extend data depth for anomaly detection.
Proves depth 2 neural networks can't approximate certain functions as well as depth 3 networks.