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

3 results for “ratio-free”

Density Ratio-Free Doubly Robust Proxy Causal Learningcs.LG

New method combines strengths of two PCL approaches without density ratio estimation.

problem Estimating causal functions in Proxy Causal Learning with unobserved confounders and proxies.

method Kernel-based doubly robust estimators combining treatment and outcome bridges, density ratio-free.

result Outperforms existing methods on PCL benchmarks, including a prior doubly robust method.

Proxy Causal Learning Doubly Robust Estimation Kernel Mean Embedding Density Ratio-Free Uniform Consistency

2025-05-26abs ↗pdf ↗

wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Modelscs.LG

wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.

problem Improving reasoning in diffusion-based large language models through RL.

method wd1: ratio-free policy optimization using weighted log-likelihood.

result wd1 outperforms diffusion-based GRPO while requiring lower computational cost.

diffusion language models reinforcement learning policy optimization ratio-free weighted log-likelihood

2025-07-07abs ↗pdf ↗

Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimationstat.ML

New method improves likelihood-free parameter estimation in complex models.

problem Estimating parameters in simulation-based models with unknown likelihood.

method Nested multi-time-scale stochastic approximation (NMTS) method.

result Eliminates bias and accelerates convergence in likelihood-free inference.

likelihood-free inference stochastic approximation parameter estimation simulation-based models multi-time-scale

2024-11-20abs ↗pdf ↗