Almanac
technique

Monte Carlo estimation

techniqueactivemonte-carlo-estimation-1f46d54a·2 events·first seen 27d ago

Aliases: Monte Carlo estimation, Monte Carlo cost estimation

Co-occurring entities

More like this (12)

Recent events (2)

5arXiv · cs.AI·27d ago·source ↗

CARV: Compute-Aware Variance Reduction for Diffusion Teacher Gradient Estimation

CARV is a hierarchical Monte Carlo estimation framework that reduces gradient variance when using frozen pretrained diffusion models as teachers in downstream pipelines such as text-to-3D distillation and data attribution. The approach amortizes expensive upstream computation (rendering, simulation, encoding) over cheap diffusion-noise resamples, augmented by timestep importance sampling and stratified-inverse-CDF construction. In text-to-3D experiments, CARV delivers 2–3× effective compute multipliers; in single-step distillation, it cuts gradient variance by an order of magnitude but does not improve FID, revealing that MC variance is not the bottleneck in that regime.

7arXiv · cs.AI·27d ago·source ↗

Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling

This paper introduces agent just-in-time (JIT) compilation as an alternative to the sequential fetch-screenshot-execute loop used by current computer-use agents. The approach compiles natural language task descriptions directly into executable code that can include LLM calls, tool calls, and parallelization, using three components: JIT-Planner, JIT-Scheduler, and an invariant-enforcing tool protocol. Across five web applications, JIT-Planner achieves 10.4× speedup and +28% accuracy over Browser-Use, while JIT-Scheduler achieves 2.4× speedup and +9% accuracy over OpenAI CUA.