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.

169,042 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “engression”

Error Analysis of Neural-Network-Based Engressionstat.ML

Engression uses neural networks to learn conditional distributions, analyzing its error components.

problem Analyzing the error in neural-network-based engression.

method Engression decomposes excess risk into approximation, stochastic, and Monte Carlo errors.

result Established convergence rates under compositional smoothness assumptions.

engression conditional distribution deep neural networks error analysis energy score

2026-07-30abs ↗pdf ↗

Engression: Extrapolation through the Lens of Distributional Regressionstat.ME

Proposes engression for extrapolation in distributional regression.

problem Challenging extrapolation problem in nonlinear regression.

method Neural network-based distributional regression.

result Engression successfully performs extrapolation under certain assumptions.

distributional regression extrapolation neural networks quantile regression pre-additive noise

2023-07-03abs ↗pdf ↗

Reverse Markov Learning: Multi-Step Generative Models for Complex Distributionscs.LG

RML improves generative modeling of complex distributions.

problem Learning complex distributions in applications.

method RML defines a forward process to a known distribution, then learns a reverse Markov process.

result RML efficiently captures complex distributions in simulations and climate data.

generative models complex distributions reverse Markov processes diffusion models scoring rules

2025-02-19abs ↗pdf ↗

Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemicsstat.ML

Deep models forecast epidemics with uncertainty quantification.

problem Accurate probabilistic forecasting of epidemics is challenging due to nonlinear temporal dependencies and spatial interactions.

method Deep spatiotemporal engression methods with geometric ergodicity and asymptotic stationarity.

result Proposed methods outperform benchmarks in point and probabilistic forecasting.

epidemics forecasting probabilistic deep learning spatiotemporal

2026-03-07abs ↗pdf ↗

ANGLE: Angular Neural Generative Learning via Engressionstat.ML

ANGLE tackles circular data regression, improving predictive performance.

problem Geometrically misleading traditional regression for circular data.

method Generative map optimized via GCES loss for non-parametric distributional regression.

result Unified toolbox for circular statistics challenges.

circular data regression generative model energy score propiety

2026-07-14abs ↗pdf ↗

Deep Generative Transformers for Probabilistic Time Series and Spatiotemporal Forecastingcs.LG

Enformer and GEnformer use Transformers with stochastic learning to forecast multivariate and spatiotemporal data with uncertainty.

problem Uncertainty quantification in multivariate time series and spatiotemporal forecasting.

method Synthesizing Transformer's expressive power with stochastic learning to model conditional distributions directly.

result Enformer and GEnformer yield calibrated probabilistic forecasts and outperform state-of-the-art baselines.

Transformer stochastic learning uncertainty quantification time series spatiotemporal forecasting

2026-03-12abs ↗pdf ↗