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.
BiQGEMM efficiently multiplies quantized DNN weights using lookup tables.
Proposes deep collective learning to learn inputs and weights together in neural networks.
NeuraLUT maps neural networks to lookup tables, reducing latency and improving expressivity.
In this paper we present a model for unsupervised topic discovery in texts corpora. The proposed model uses documents, words, and topics lookup table embedding as neural network model parameters to build probabilities of words given topics, and probabilities of topics given documents. These probabilities are used to re…
Efficient algorithm computes knot invariants quickly.
We describe a high performance parallel implementation of a derivative pricing model, within which we introduce a new parallel method for the calibration of the industry standard SABR (stochastic-αβρ) stochastic volatility model using three strike inputs. SABR calibration involves a non-linear three dimensional minimis…
The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on performance on a test set or on bounds from model complexity. We propose a famil…
In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach results in networks that are free of floating-point operations and free of multiplications, suitable for direct FPGA and ASIC implementation…
Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most u…
We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to c…
Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision trees are sma…
Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the abstractions required for such patterns are simple. In this paper, we first review …
Many poker systems, whether created with heuristics or machine learning, rely on the probability of winning as a key input. However calculating the precise probability using combinatorics is an intractable problem, so instead we approximate it. Monte Carlo simulation is an effective technique that can be used to approx…
This paper describes a conditional neural network architecture for Mandarin Chinese polyphone disambiguation. The system is composed of a bidirectional recurrent neural network component acting as a sentence encoder to accumulate the context correlations, followed by a prediction network that maps the polyphonic charac…
The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention lookup scale linearly in the size of the attended sequence. Second, it does not enc…
Bayesian networks are probabilistic graphical models widely employed to understand dependencies in high dimensional data, and even to facilitate causal discovery. Learning the underlying network structure, which is encoded as a directed acyclic graph (DAG) is highly challenging mainly due to the vast number of possible…
The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes. Simulators need to model output variables related to circuit timing, power, noise, etc.,…
PolyLUT uses polynomials to reduce FPGA latency.
Collaborative filtering, especially latent factor model, has been popularly used in personalized recommendation. Latent factor model aims to learn user and item latent factors from user-item historic behaviors. To apply it into real big data scenarios, efficiency becomes the first concern, including offline model train…
Gradient-based framework for optimizing text prompts in diffusion models.
This paper uses graph convolutional networks to improve the accuracy of neural architecture search.
Revisit Fenn's table theorem from a differential-topological perspective.
EikoNet uses deep learning to solve the Eikonal equation quickly and efficiently.
Study detects synthetic tabular data across different tables.
Proves a generalized table theorem for odd Euler characteristic surfaces.
Deep models store facts in geometric embeddings, not just associative memory.
CTSyn generates high-quality synthetic tabular data.
Upper bounds for surface-links in the Yoshikawa table are estimated.
Survey of reinforcement learning guarantees with data constraints.
This paper compiles and calculates triple point numbers for surface-links in Yoshikawa's table.
The paper proves geometric properties of square tables and saddle surfaces.
Two new techniques improve zero-shot HPO efficiency.
In this paper, a spintronic neuromorphic reconfigurable Array (SNRA) is developed to fuse together power-efficient probabilistic and in-field programmable deterministic computing during both training and evaluation phases of restricted Boltzmann machines (RBMs). First, probabilistic spin logic devices are used to devel…
Machine learning speeds up search procedures for sorted tables.
Historical (Stressed-) Value-at-Risk ((S)VAR), and Expected Shortfall (ES), are widely used risk measures in regulatory capital and Initial Margin, i.e. funding, computations. However, whilst the definitions of VAR and ES are unambiguous, they depend on input distributions that are data-cleaning- and Data-Model-depende…
Method finds differential equations for integrable billiard tables.
Billiard trajectories and geodesics are closely related geometrically.
This document contains tables with the classification of prehomogeneous modules for reductive algebraic groups with up to two simple factors due to Sato, Kimura and many others, as well as corresponding tables of the étale modules appearing in this list, determined by the author. It is intended as a convenient referenc…
BiN normalizes financial time-series for better forecasting.
Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their d…
This note corrects errors in Hatcher and Oertel's table of boundary slopes of Montesinos knots which have projections with 10 or fewer crossings.
In 1869, the first draft of the periodic table was published by Russian chemist Dmitri Mendeleev. In terms of data science, his achievement can be viewed as a successful example of feature embedding based on human cognition: chemical properties of all known elements at that time were compressed onto the two-dimensional…
Compactness proven for isospectral Birkhoff billiard tables.
Method combines clustering and matrix completion for missing data in I/O tables.
Proposes -table for statistical SHAP explanations in regression models.
We give a complete characterization of the relationship between the shape of a Euclidean polygon and the symbolic dynamics of its billiard flow. We prove that the only pairs of tables that can have the same bounce spectrum are right-angled tables that differ by an affine map. The main tool is a new theorem that establi…
To study embeddings of tangles in knots, we use quandle cocycle invariants. Computations are carried out for the tables of knots and tangles, to investigate which tangles may or may not embed in knots in the tables.
Robotic table tennis learns efficient policies to return balls at 100Hz.