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 “W2-distance”

Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distancestat.ML

Improves SGM convergence bounds in W2-distance without strict assumptions.

problem Convergence bounds for SGMs in W2-distance require stringent assumptions.

method Novel framework using the OU process and PDE analysis.

result Log-concavity evolves from weak to strong over time.

Score-based Generative Models W2-distance Convergence bounds Ornstein-Uhlenbeck process PDE analysis

2025-01-04abs ↗pdf ↗

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularizationcs.LG

Proposes a new RL method to fine-tune flow-based models with arbitrary rewards.

problem Challenges in fine-tuning continuous flow-based generative models with arbitrary reward functions.

method Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regularization (ORW-CFM-W2)

result Achieves optimal policy convergence with controllable trade-offs between reward maximization and diversity preservation.

reinforcement learning flow-based models reward maximization policy optimization Wasserstein-2 regularization

2025-02-09abs ↗pdf ↗

Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Samplingstat.ML

New algorithms improve sampling from constrained distributions.

problem Sampling from distributions constrained to convex bodies.

method Penalized Langevin Dynamics and Underdamped Monte Carlo methods.

result Improved convergence rates for constrained sampling problems.

Langevin Monte Carlo Convex Optimization Constrained Sampling Underdamped Dynamics Penalty Methods

2022-11-29abs ↗pdf ↗