Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

69137206274 · May 202619922001200920172026
48 results for Causal residual Transformers

Framework calculates positional influence in causal residual Transformers.

problem Understanding positional influence in causal residual Transformers.
method Adjoint-sensitivity framework for positional influence in causal residual Transformers.
result Exact evolution of adjoint-energy influence density and decomposition into residual transmission, nonlocal Volterra, and local channels.

LANCA uses ANM to learn latent causal factors without supervision.

problem Learning latent causal factors without supervision.
method LANCA employs a deterministic Wasserstein Auto-Encoder coupled with a differentiable ANM Layer.
result LANCA outperforms baselines on physics and photorealistic environments.

CRC improves multivariate forecasting accuracy without risking performance degradation.

problem Systematic errors and lack of guarantees in multivariate forecasters.
method CRC uses a causality-inspired encoder and hybrid corrector with a safety mechanism.
result CRC consistently improves accuracy and ensures high non-degradation rates.

Causality-aware methods outperform linear residualization in confounding adjustment for anticausal prediction.

problem Adjusting for confounding in anticausal prediction tasks.
method Causality-aware counterfactual confounding adjustment.
result Causality-aware methods asymptotically outperform linear residualization in predictive performance.

Proposes a neural network method to correct residual distortions in coordinate transformations.

problem Nonlinear and spatially dependent distortions in coordinate transformation models.
method Residual-based neural network approach focusing on systematic distortions.
result The method improves accuracy and stability in challenging conditions.

GaussDetect-LiNGAM eliminates Gaussianity tests for causal discovery.

problem Causal direction identification without Gaussianity assumptions.
method Leverages the equivalence between noise Gaussianity and residual independence in reverse regression.
result Gaussianity tests replaced with robust kernel-based independence tests.

New method uses observational data to improve trial design efficiency.

problem Scarce randomized controlled trials; inefficiency of using observational data.
method Active Residual Learning, R-Design framework, R-EPIG criterion.
result Efficiently estimating residuals to correct observational bias improves trial design.

Alternative to likelihood-based LSNM model selection, residual independence testing is more robust to noise misspecification.

problem Cause-effect inference in location-scale noise models with misspecified noise distributions.
method Residual independence testing as an alternative to likelihood-based model selection.
result Residual independence testing is more robust to noise misspecification.

We provide theoretical and empirical evidence for a type of asymmetry between causes and effects that is present when these are related via linear models contaminated with additive non-Gaussian noise. Assuming that the causes and the effects have the same distribution, we show that the distribution of the residuals of …

2014-09-16abs ↗pdf ↗

A new model improves CT image quality from low-dose scans.

problem Improving CT image quality from low-dose scans.
method Multi-layer Residual Sparsifying Transform (MRST) learning model for low-dose CT reconstruction.
result The MRST model outperforms conventional methods in maintaining subtle details.

Framework isolates causal effects from time series data, improving accuracy under non-stationarity and autocorrelation.

problem Causal inference in non-stationary, autocorrelated time series data.
method Decomposes time series into trend, seasonal, and residual components; performs component-specific causal analysis.
result Framework more accurately recovers ground-truth causal structure than state-of-the-art baselines, especially under strong non-stationarity and temporal autocorrelation.

Transformer-based method for causal discovery with prior knowledge integration.

problem Complex nonlinear dependencies and spurious correlations in time series data.
method Multi-layer Transformer forecaster with gradient-based causal structure extraction and attention masking for prior knowledge integration.
result Significant improvement in causal discovery and causal lag estimation compared to state-of-the-art methods.

Paper characterizes and represents pairwise causal background knowledge for improved causal inference.

problem Improving causal inference by handling pairwise causal constraints.
method Graphical characterization, direct causal clause (DCC), unified representation, MPDAG, polynomial-time algorithms.
result Pairwise causal background knowledge uniquely decomposes into MPDAG and DCCs, improving causal effect identification.

New framework learns nonlinear cyclic causal models from data.

problem Challenges in learning causal relationships from real-world, cyclic systems.
method NODAGS-Flow: a novel framework using residual normalizing flows for likelihood estimation.
result Significant performance improvements in structure recovery and predictive performance compared to state-of-the-art methods.

S-DIDML integrates structural DID with ML for causal inference in high-dimensional data.

problem Causal inference in high-dimensional observational panel data with confounding variables.
method Structural identification with high-dimensional estimation, Neyman orthogonality, cross-fitting, causal forests, semi-parametric models.
result Precision in identifying policy-sensitive groups and optimizing resource allocation.

This work tackles OOD generalization by leveraging causal invariance without needing to recover causal features.

problem Learning models that perform well on out-of-distribution (OOD) data.
method Causal invariant transformations to modify non-causal features while preserving causal parts.
result Theoretical and practical methods to learn a minimax optimal model across domains using single domain data.

A neural network approach uncovers Granger causality without explicit variable selection.

problem Capturing complex associations in multivariate time series data.
method A deep learning model with proper regularization to learn the true Granger Causality structure.
result A neural network can learn the true Granger Causality structure from data without explicit variable selection.

Two methods are proposed to filter correlations in DCC-GARCH residuals for foreign exchange rates.

problem Filtering correlations in DCC-GARCH residuals for accurate foreign exchange rate prediction.
method Two approaches: estimating correlation matrix as a parameter and using eigenvalue decomposition.
result The DCC-GARCH residual can be almost independent using these methods.

Causal inference uses observations to infer the causal structure of the data generating system. We study a class of functional models that we call Time Series Models with Independent Noise (TiMINo). These models require independent residual time series, whereas traditional methods like Granger causality exploit the var…

2012-07-21abs ↗pdf ↗

CaTs use DAGs with transformers to enforce causal constraints, improving neural network robustness.

problem Neural networks lack inherent causal structure respect, leading to reliability issues.
method Introducing Causal Transformers (CaTs) that operate under predefined causal constraints specified by DAGs.
result CaTs improve robustness and interpretability of neural networks under causal constraints.

This paper tackles causal representation learning with linear and general transformations.

problem Identify and recover latent causal variables and graphs under unknown transformations.
method Score-based algorithms that use gradients of log-density functions for identifiability and achievability.
result Two stochastic hard interventions per node are sufficient for identifiability of general transformations.

Paper recovers latent causal structure and linear transformation from indirect observations.

problem Recovering latent causal structure and linear transformation from indirect observations.
method Established sufficient conditions for DAG recovery, leveraged score function properties, and used soft/hard interventions.
result Perfect recovery of latent DAG structure and linear transformation up to scaling using soft interventions, hard interventions with additional hypothesis testing.

Based on the recent work \cite{PII} we put forward a new type of transformation for Lorentzian manifolds characterized by mapping every causal future-directed vector onto a causal future-directed vector. The set of all such transformations, which we call causal symmetries, has the structure of a submonoid which contain…

2003-03-05abs ↗pdf ↗

Researchers prove Transformers are Turing-complete and analyze their components.

problem Understanding the computational power and limitations of Transformers.
method Analyzed Turing-completeness of vanilla and modified Transformers, and necessity of components.
result Transformers with positional masking and positional encodings are Turing-complete.

Develops a Causal Transformer for estimating counterfactual outcomes from longitudinal data.

problem Estimating counterfactual outcomes over time from observational data is challenging due to complex, long-range dependencies.
method Combines three transformer subnetworks with separate inputs for time-varying covariates, previous treatments, and previous outcomes into a joint network with in-between cross-attentions. Uses a custom, end-to-end training procedure with a counterfactual domain confusion loss to address confounding bias.
result Achieves superior performance over current baselines in synthetic and real-world datasets.

We define a new type of transformation for Lorentzian manifolds characterized by mapping every causal future-directed vector onto a causal future-directed vector. The set of all such transformations, which we call causal symmetries, has the structure of a submonoid. Some of their properties are investigated and we give…

2002-11-29abs ↗pdf ↗

CSHT predicts financial returns from news using a novel transformer model on a sphere.

problem Financial forecasting from news and sentiment.
method Granger-causal hypergraph structure, Riemannian geometry, causally masked Transformer attention.
result CSHT outperforms baselines in return prediction, regime classification, and asset ranking.

Flow models recover causal transformations from observational data and a valid ordering.

problem Causal inference with only observational data and a valid causal ordering.
method Flow models that can recover component-wise, invertible transformations of exogenous variables.
result Flow models outperform previous methods and deliver consistent performance across various structural causal models.

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …

2017-03-30abs ↗pdf ↗

We prove the homotopy invariance of L^2 torsion for covering spaces, whenever the covering transformation group is either residually finite or amenable. In the case when the covering transformation group is residually finite and when the L^2 cohomology of the covering space vanishes, the homotopy invariance was establi…

1997-06-06abs ↗pdf ↗

Study Transformer layers under cross-entropy training using mean field control.

problem Understanding the behavior of Transformer layers in cross-entropy training.
method Continuous-depth mean field control analysis, treating depth as time and layer parameters as controls.
result Derivation of a Pontryagin condition for the limiting population problem, involving the softmax residual.

Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only Lipschitz conditions rather than strict architectural constraints are needed for enforci…

2019-06-06abs ↗pdf ↗

The study explores how Transformers predict the next token in a sequence.

problem Understanding the mechanism behind Transformers' autoregressive learning ability.
method Exploring the approximation ability of Transformers for next-token prediction through specific instances and a causal kernel descent method.
result Transformer models can learn context-dependent functions ff for next-token prediction based on past and current observations.

Introduces Causal Energy Minimization to understand Transformer layers.

problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.

This paper introduces a new task to better understand Transformers in quantitative contexts.

problem Understanding Transformers in high-stakes quantitative and scientific applications.
method Introduces a novel contextual counting task and analyzes it with causal and non-causal Transformer architectures.
result Causal attention is better suited for the contextual counting task, and no positional embeddings lead to the best accuracy.