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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “error-compounding”

A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learningcs.LG

Clarifies model-based RL's theoretical issues and counterexamples for popular losses.

problem Model-based reinforcement learning's empirical performance vs. theoretical properties and popular loss functions.

method Analyzes empirical and theoretical aspects of model-based RL and constructs counterexamples for losses.

result MuZero loss fails in stochastic and deterministic environments, leading to exponential sample complexity.

reinforcement learning model-based loss functions error compounding MuZero

2024-04-15abs ↗pdf ↗

Robust Orthogonal Machine Learning of Treatment Effectsstat.ML

New method offsets DML's error-compounding issue and provides more stable causal parameter estimates.

problem Estimating ATE from observational data with robustness and stability.

method Robust Causal Learning (RCL) method to offset DML's deficiencies.

result RCL estimators are more stable and perform better than DML and traditional estimators.

causal learning average treatment effect DML error-compounding propensity scores

2021-03-22abs ↗pdf ↗

Robust Causal Learning for the Estimation of Average Treatment Effectsecon.EM

Proposes RCL method to improve ATE estimation from observational data.

problem Error-compounding issue and extreme estimates in DML estimators.

method Robust Causal Learning (RCL) method to offset DML deficiencies.

result RCL estimators are more stable and perform better than DML estimators.

ATE estimation observational study Double/Debiased Machine Learning propensity scores error-compounding

2022-09-05abs ↗pdf ↗

Stabilising Lifetime PD Models under Forecast Uncertaintyq-fin.RM

The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.

problem Stable estimation of lifetime PDs under forecast uncertainty.

method Reformulated in state-space framework, introduced an anchored observation model.

result Asymptotic stochastic stability of error dynamics, leading to smoother projections.

PD estimation Kalman filter forecast uncertainty stochastic stability state-space model

2025-09-12abs ↗pdf ↗

On Generalization Bounds for Deep Compound Gaussian Neural Networksstat.ML

The paper develops generalization bounds for deep compound Gaussian neural networks.

problem Developing theoretical guarantees for the performance of deep neural networks.

method Novel generalization error bounds using a compound Gaussian prior and Dudley's integral.

result Theoretical bounds show generalization error scales

\mathcal{O}(n\sqrt{\ln(n)})

in signal dimension and

\mathcal{O}((Network Size)^{3/2})

in network size.

Deep Neural Networks Generalization Error Compound Gaussian Rademacher Complexity Dudley's Integral

2024-02-20abs ↗pdf ↗

PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Managementcs.AI

PortBench benchmarks LLMs for PM, revealing their weaknesses in diversification and robustness.

problem Lack of benchmarks for LLM-driven portfolio management, especially in diversification and robustness.

method Developed a comprehensive benchmark with a static QA dataset and a dynamic allocation pipeline, introducing metrics to evaluate correlation and robustness.

result 90% of LLMs fail to outperform a basic equal-weight allocation, highlighting their limitations in diversification and robustness.

portfolio management large language models correlation robustness stress testing

2026-05-27abs ↗pdf ↗

Feedback in Imitation Learning: The Three Regimes of Covariate Shiftcs.LG

New approach mitigates feedback divergence in imitation learning.

problem Divergence between held-out error and learner performance in imitation learning.

method Identifies covariate shift as the root cause and proposes a simulator-based solution.

result Naive behavioral cloning performs well in real-world decision making problems.

Imitation Learning Covariate Shift Feedback Divergence Simulator Behavioral Cloning

2021-02-04abs ↗pdf ↗

Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimallycs.LG

New algorithm reduces suboptimality in imitation learning to nearly optimal levels.

problem Statistical limits of imitation learning in MDPs with known transitions.

method Mimic-MD algorithm and reduction to value estimation problem.

result Upper bound of

O(|\mathcal{S}|H^{3/2}/N)

for suboptimality, with efficient computation.

Imitation Learning Markov Decision Processes Known Transitions Suboptimality Value Estimation

2021-02-25abs ↗pdf ↗