arXiv research

SPX optimizes multiple graph drawing metrics for better readability.

RL for image captions improved with a language prior.

SigD2 reduces noisy rules in rule-based classifiers for better accuracy and readability.

A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.

Automatically extracts hyperparameter schemas from AI library documentation.

Computer-generated proofs led to a mathematical result.

Team QCRI-MIT detects hyperpartisan news with 72.9% accuracy.

We show that the action of the mapping class group on bordered Floer homology in the second to extremal spin^c-structure is faithful. This paper is designed partly as an introduction to the subject, and much of it should be readable without a background in Floer homology.

The six nondegeneracy conditions of geometric nature that are satisfied by the only six possibly existing nondegenerate general classes I, II, III-1, III-2, IV-1, IV-2 of 5-dimensional CR manifolds are shown to be readable instantaneously from their elementarily normalized respective defining graphed equations, without…

Solves the challenge of retrieving item-specific financial information from Form 10-Q filings.

The simulator is an R package that streamlines the process of performing simulations by creating a common infrastructure that can be easily used and reused across projects. Methodological statisticians routinely write simulations to compare their methods to preexisting ones. While developing ideas, there is a temptatio…

In this text I present some problems which led to the introduction of special kinds of graphs as tools for studying singular points of algebraic surfaces. I explain how such graphs were first described using words, and how several classification problems made it necessary to draw them, leading to the elaboration of a s…

Generative Map learns interpretable neural network maps for camera localization.

Given a Morse function f on a closed manifold M with distinct critical values, and given a field F, there is a canonical complex, called the Morse-Barannikov complex, which is equivalent to any Morse complex associated with f and whose form is simple. In particular, the homology of M with coefficients in F is immediate…

We present the mathematical background of a software package that computes triangulations of mapping tori of surface homeomorphisms, suitable for Jeff Weeks's program SnapPea. It consists of two programs. jmt computes triangulations and prints them in a human-readable format. jsnap converts this format into SnapPea's t…

This article demonstrates that convolutional operation can be converted to matrix multiplication, which has the same calculation way with fully connected layer. The article is helpful for the beginners of the neural network to understand how fully connected layer and the convolutional layer work in the backend. To be c…

Our interest in this paper is in the construction of symbolic explanations for predictions made by a deep neural network. We will focus attention on deep relational machines (DRMs, first proposed by H. Lodhi). A DRM is a deep network in which the input layer consists of Boolean-valued functions (features) that are defi…

We consider the problem of finding the minimizer of a function $f: \mathbb{R}^d \rightarrow \mathbb{R}$ of the finite-sum form $\min f(w) = 1/n\sum_{i}^n f_i(w)$. This problem has been studied intensively in recent years in the field of machine learning (ML). One promising approach for large-scale data is to use a stoc…

Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT) in Python. It takes numeric functions written in a syntactic subset of Python and NumPy as input, and generates new Python functions which c…

This paper proposes an organized generalization of Newman and Girvan's modularity measure for graph clustering. Optimized via a deterministic annealing scheme, this measure produces topologically ordered graph clusterings that lead to faithful and readable graph representations based on clustering induced graphs. Topog…

Tracr compiles programs into transformer models for interpretability.

Paper provides a rigorous proof of the index theorem for economists.

This is an introduction to the subject of the differential topology of the space of smooth loops in a finite dimensional manifold. It began as the background notes to a series of seminars given at NTNU and subsequently at Sheffield. I am posting them in the hope that they will be useful to people wishing to know a litt…

Paper tackles score following in full-page sheet music images.

LLMs can help explain credit risk models but not autonomously.

A substantial progress in development of new and efficient tensor factorization techniques has led to an extensive research of their applicability in recommender systems field. Tensor-based recommender models push the boundaries of traditional collaborative filtering techniques by taking into account a multifaceted nat…

MRCpy implements minimax risk classifiers with performance guarantees and distribution shift adaptability.

Transformer model improves source code summarization.

VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.

System suggests clinical concepts in real-time for faster note creation.

Torch-Struct simplifies structured prediction for deep learning.

OutlierTree detects outliers using decision trees and provides explanations.

NFTs with diverse rare attributes sell at higher prices.

Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthet…

Benchmark for math reasoning models from human proofs.

NCVis speeds up data visualization for large datasets.

Text clustering method replaces centroids with summaries for interpretability and scalability.

In this article, we propose the Coopetititve Soft Gating Ensemble or CSGE for general machine learning tasks and interwoven systems. The goal of machine learning is to create models that generalize well for unknown datasets. Often, however, the problems are too complex to be solved with a single model, so several model…

Discover governing equations from data without specifying terms.

Paper teaches robots to play piano with touch and learning.

In 1970, E. M. Andreev published a classification of all three-dimensional compact hyperbolic polyhedra having non-obtuse dihedral angles. Given a combinatorial description of a polyhedron, $C$, Andreev's Theorem provides five classes of linear inequalities, depending on $C$, for the dihedral angles, which are necessar…

Enhances machine learning for high-energy physics data by embedding feature construction.

New system tracks musical performances in raw sheet images without preprocessing.

A novel unsupervised feature selection method using subspace clustering and self-expressive model.

Data analysis in high-dimensional spaces aims at obtaining a synthetic description of a data set, revealing its main structure and its salient features. We here introduce an approach providing this description in the form of a topography of the data, namely a human-readable chart of the probability density from which t…

Proposes a method to reveal nonlinearities in tensor data.

We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents polic…

It seems to be very unlikely that all relevant information in the stock market could be fully encoded in a geometrical shape. Still,the present paper will reveal the geometry behind the stock market transactions. The prices of market index (DJIA) stock components are arranged in ascending order from the smallest one in…