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.
New model generates realistic single-cell gene expression data.
We present a technique to characterize differentially expressed genes in terms of their position in a high-dimensional co-expression network. The set-up of Gaussian graphical models is used to construct representations of the co-expression network in such a way that redundancy and the propagation of spurious informatio…
Express improves causal attention guarantees for language models.
PNCs balance tractability and expressiveness in probabilistic modeling.
This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.
This work explores the relationship between expressivity and generalization in GNNs.
Identifying latent structure in large data matrices is essential for exploring biological processes. Here, we consider recovering gene co-expression networks from gene expression data, where each network encodes relationships between genes that are locally co-regulated by shared biological mechanisms. To do this, we de…
The paper introduces closed-form expressions for interpreting Tsetlin Machines.
New model captures complex relationships from experimental data.
Study shows limits of certain normalizing flows in higher dimensions.
Higher granularity in MoE models boosts expressivity exponentially.
New findings show strategic interactions can undermine model expressiveness in machine learning.
Motivation: Public and private repositories of experimental data are growing to sizes that require dedicated methods for finding relevant data. To improve on the state of the art of keyword searches from annotations, methods for content-based retrieval have been proposed. In the context of gene expression experiments, …
SimCD simultaneously clusters cells and identifies differential gene expression in scRNA-seq data.
Study reveals Transformer's expressive power and mechanisms.
This paper compares HMC and RNN expressivity using SRT.
Obtaining a non-parametric expression for an interventional distribution is one of the most fundamental tasks in causal inference. Such an expression can be obtained for an identifiable causal effect by an algorithm or by manual application of do-calculus. Often we are left with a complicated expression which can lead …
Stem uses diffusion models to infer gene expression from H&E images.
Cataloging the neuronal cell types that comprise circuitry of individual brain regions is a major goal of modern neuroscience and the BRAIN initiative. Single-cell RNA sequencing can now be used to measure the gene expression profiles of individual neurons and to categorize neurons based on their gene expression profil…
Token-adaptive FFN design improves LLM expressivity.
Survey on GNNs' power and limitations.
We present a Bayesian hierarchical multi-view mixture model termed Symphony that simultaneously learns clusters of cells representing cell types and their underlying gene regulatory networks by integrating data from two views: single-cell gene expression data and paired epigenetic data, which is informative of gene-gen…
New method infers co-expression networks robustly from multiple studies.
Implicit models can match or exceed explicit models with more test-time compute.
This paper addresses the problem of inferring a regular expression from a given set of strings that resembles, as closely as possible, the regular expression that a human expert would have written to identify the language. This is motivated by our goal of automating the task of postmasters of an email service who use r…
We introduce normalized nonnegative models (NNM) for explorative data analysis. NNMs are partial convexifications of models from probability theory. We demonstrate their value at the example of item recommendation. We show that NNM-based recommender systems satisfy three criteria that all recommender systems should ide…
With the wealth of high-throughput sequencing data generated by recent large-scale consortia, predictive gene expression modelling has become an important tool for integrative analysis of transcriptomic and epigenetic data. However, sequencing data-sets are characteristically large, and previously modelling frameworks …
We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent representation. Additional latent variables account for technical effects that may erroneously set some observations of gene expression leve…
When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressive generative models in complex environments. We show that a predictive algorithm with an expressive generative model can form stable belief-…
Researchers derive an analytic expression for Gaussian stochastic volatility models.
GNNs with random node initialization are shown to be universally expressive.
Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based queries. We propose a reinforcement-learning-driven translation model framework able to 1) learn the translation from NL expressions to que…
In the present work, we propose a new multifactor stochastic volatility model in which slow factor of volatility is approximated by a parabolic arc. We retain ourselves to the perturbation technique to obtain approximate expression for European option prices. We introduce the notion of modified Black-Scholes price. We …
Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying landscape of DL models and hardware platforms presents challenging tradeoffs betwee…
We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent representation. Additional latent variables account for technical effects that may erroneously set some observations of gene expression leve…
Deep neural networks approximate option prices in high-dimensional Lévy models efficiently.
Neural network-based Open-ended conversational agents automatically generate responses based on predictive models learned from a large number of pairs of utterances. The generated responses are typically acceptable as a sentence but are often dull, generic, and certainly devoid of any emotion. In this paper, we present…
Study bounds VAR model's circuit complexity, showing it's limited to TC^0 circuits.
New architectures improve topological deep learning's ability to capture complex data features.
LEM efficiently models long-term sequences with gradients.
Next-generation sequencing (NGS) to profile temporal changes in living systems is gaining more attention for deriving better insights into the underlying biological mechanisms compared to traditional static sequencing experiments. Nonetheless, the majority of existing statistical tools for analyzing NGS data lack the c…
Enhances quantum machine learning models using Fock states.
We investigate graph neural networks for multi-relational data.
Paper provides an explicit formula for local volatility in Cheyette models.
Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of . Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are underexplored. …
Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressive power of graph neural networks (GNN). It was shown that the popular message passing GNN cannot distinguish between graphs that are indistinguishable by the 1-WL test (Morris et al. 2018; Xu et al. 2019). Unfortunately, many s…
Deep Heaviside networks are limited but can be improved with connections or linear neurons.
Paper proposes dp-VAE for preserving spatial context in gene expression data.