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.
Model predicts traffic speed using urban incidents.
New statistical models for predicting ranked preferences from partial orders.
New method learns decisions from collective preferences without individual covariates.
Recent progress in separating the speech signals from multiple overlapping speakers using a single audio channel has brought us closer to solving the cocktail party problem. However, most studies in this area use a constrained problem setup, comparing performance when speakers overlap almost completely, at artificially…
This paper analyzes Airbnb listings in the city of San Francisco to better understand how different attributes such as bedrooms, location, house type amongst others can be used to accurately predict the price of a new listing that optimal in terms of the host's profitability yet affordable to their guests. This model i…
Paper predicts crimes using historical data and machine learning.
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…
This paper explores integration and contagion among US metropolitan housing markets. The analysis applies Federal Housing Finance Agency (FHFA) house price repeat sales indexes from 384 metropolitan areas to estimate a multi-factor model of U.S. housing market integration. It then identifies statistical jumps in metrop…
This paper analyzes consumer choices over lunchtime restaurants using data from a sample of several thousand anonymous mobile phone users in the San Francisco Bay Area. The data is used to identify users' approximate typical morning location, as well as their choices of lunchtime restaurants. We build a model where res…
SANs estimate feature importance in neural models, identifying interactions and high-ranked features.
SANS uses graph structure to find meaningful negatives for entity and relation embeddings.
SANs use sparse activation functions to compress data representations.
Paper proposes SAN and SN for zero-shot sketch-based image retrieval.
Transfer learning improves highway traffic forecasting using graph neural networks.
Let be a nontrivial knot. The Cabling Conjecture of Francisco González-Acuña and Hamish Short posits that -Dehn surgery on produces a reducible manifold if and only if is a -cable knot and the surgery slope equals . We extend the work of James Allen Hoffman to prove the Cabling …
Recently Francisco Presas Mata constructed the first examples of closed contact manifolds of dimension larger than 3 that contain a plastikstufe, and hence are non-fillable. Using contact surgery on his examples we create on every sphere S^{2n-1}, n>1, an exotic contact structure ξ_- that also contains a plastikstufe. …
Previous literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features. However, this was done without considering the description length of the learned representations which is a direct and unbiased measure of the model complexity. In this paper, first we intro…
ST-SAN predicts flow with spatial-temporal dependencies using self-attention.
Replacing Black-Scholes' driving process, Brownian motion, with fractional Brownian motion allows for incorporation of a past dependency of stock prices but faces a few major downfalls, including the occurrence of arbitrage when implemented in the financial market. We present the development, testing, and implementatio…
In the first part of this paper, we consider smooth maps from a compact orientable 3-manifold without boundary to the 2-sphere. We give a geometric criterion to decide whether two given maps are homotopic, based on the sets of points where the maps are equal or antipodal. We extend this criterion to non-singular vector…
Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.
Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications h…
On every compact, orientable, irreducible 3-manifold V which is toroidal or has torus boundary components we construct a contact 1-form whose Reeb vector field R does not have any contractible periodic orbits and is tangent to the boundary. Moreover, if bdry V is nonempty, then the Reeb vector field R is transverse to …
Scheduling surgeries is a challenging task due to the fundamental uncertainty of the clinical environment, as well as the risks and costs associated with under- and over-booking. We investigate neural regression algorithms to estimate the parameters of surgery case durations, focusing on the issue of heteroscedasticity…
In his book with Alan Jolis, Vers un monde sans pauvreté (1997) Yunus gives the example of a microcredit loan of 1000BDT reimbursed via 50 weekly settlements of 22BDT and correctly claims that this corresponds to the annual interest rate of 20%. But this is without taking into account that if the borrower has good reas…
Improved resource allocation method reduces procurement costs.
Deep learning models learn chaotic system dynamics from real and simulated data.
In the United States, heart disease is the leading cause of death for both men and women, accounting for 610,000 deaths each year [1]. Physicians use Magnetic Resonance Imaging (MRI) scans to take images of the heart in order to non-invasively estimate its structural and functional parameters for cardiovascular diagnos…
Study compares survival analysis algorithms with missing data methods.