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.
Framework for interpreting ML models to reveal properties of real-world phenomena.
Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specifying objectives or desired attributes. In this paper, we identify the key properties used to interpret automata and propose a modification o…
Develops a learning algorithm for PSL formulas from examples.
The paper builds interpretable models for property markets using machine learning.
New definition of interpretability makes model design more actionable.
Understanding biological network dynamics is a fundamental issue in various scientific and engineering fields. Network theory is capable of revealing the relationship between elements and their propagation; however, for complex collective motions, the network properties often transiently and complexly change. A fundame…
Study geodesic properties of time series data using Wasserstein metric.
BL learns interpretable optimization structures from data.
Interpretable representations improve explainable AI by translating complex data into understandable concepts.
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable mo…
Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…
Generative model learns to create molecules with multiple properties using interpretable substructures.
Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive v…
Chemical databases store information in text representations, and the SMILES format is a universal standard used in many cheminformatics software. Encoded in each SMILES string is structural information that can be used to predict complex chemical properties. In this work, we develop SMILES2vec, a deep RNN that automat…
MV-GNN improves molecular property prediction by integrating atom and bond information.
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension betw…
C2G-Net improves image classification of similar objects like cells.
DiSeNE generates interpretable node embeddings without supervision.
The notion of a Dirac submanifold of a Poisson manifold was studied by Xu (arXiv:math.SG/0110326). We give an interpretation of Xu's definition in terms of a general notion of tensor fields soldered to a normalized submanifold. Then, this interpretation is used to define Dirac submanifolds of a Jacobi manifold. Several…
Drug similarity has been studied to support downstream clinical tasks such as inferring novel properties of drugs (e.g. side effects, indications, interactions) from known properties. The growing availability of new types of drug features brings the opportunity of learning a more comprehensive and accurate drug similar…
The paper connects decision tree interpretability and robustness through separation.
GMT improves interpretability of XGNNs by approximating SubMT.
Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks. By analyzing the properties of neural networks as operators on probability distributions for observed data, we show that the distribu…
We propose a novel interpretation of the collapsed variational Bayes inference with a zero-order Taylor expansion approximation, called CVB0 inference, for latent Dirichlet allocation (LDA). We clarify the properties of the CVB0 inference by using the alpha-divergence. We show that the CVB0 inference is composed of two…
With the rise of deep neural networks for quantum chemistry applications, there is a pressing need for architectures that, beyond delivering accurate predictions of chemical properties, are readily interpretable by researchers. Here, we describe interpretation techniques for atomistic neural networks on the example of …
New compactification for character varieties with good topological properties.
MAT uses attention mechanism for molecule property prediction.
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses. Unlike in a standard multi-class classification setting, misclassification cost…
GAMLA learns manifold structures with auto-encoding for global insights.
Unified approach to verify NN properties using ReLU's unique polytope structure.
This paper is devoted to the problem of choosing the most suitable model of a geometrical system for describing the real crystallographic space. It has been shown that all 230 crystallographic groups used to describe the crystalline structures in a Euclidean space can be presented by elliptic motions in the closed spac…
FF layers in transformers are nearly as interpretable as sparse autoencoders.
New method interprets quantum many-body snapshots for phase detection.
NAMLSS models provide interpretable neural regression for location, scale, and shape.
Develops an ordinal-similarity framework for scalable and interpretable representation alignment.
AWD distills neural network info into interpretable wavelets.
With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties. While these approaches have improved performance in graph machine learning tasks compared to traditional graph techniques, they are still perceived as techniques with limite…
The current interpretation of stochastic gradient descent (SGD) as a stochastic process lacks generality in that its numerical scheme restricts continuous-time dynamics as well as the loss function and the distribution of gradient noise. We introduce a simplified scheme with milder conditions that flexibly interprets S…
Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensional image distributions. More recent generative models leverage the power of neural networks to implicitly learn and represent probability …
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked …
Mathematical properties of the historical GDP/cap distributions are discussed and explained. These distributions are frequently incorrectly interpreted and the Unified Growth Theory is an outstanding example of such common misconceptions. It is shown here that the fundamental postulates of this theory are contradicted …
A new model combines diffusion and random features for better interpretability and comparable performance.
New framework aims to make neural network explanations more reliable.
The paper formalizes feature attribution to address inconsistent definitions and evaluate methods.
Convolutional neural networks (CNNs) are one of the driving forces for the advancement of computer vision. Despite their promising performances on many tasks, CNNs still face major obstacles on the road to achieving ideal machine intelligence. One is that CNNs are complex and hard to interpret. Another is that standard…
MARLeME extracts MARL models into symbolic models for better interpretability.
This manuscript proposes a probabilistic framework for algorithms that iteratively solve unconstrained linear problems with positive definite for . The goal is to replace the point estimates returned by existing methods with a Gaussian posterior belief over the elements of the inverse of , which can …
Simplifies PLNNs to interpretable models for better explainability.