JHU Computer Science

jhucompsci.bsky.social

12 July 2026 05:22

“No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference” by @moberst.bsky.social, Pranav Mani, Peng Xu, and @zacharylipton.bsky.social conducts an exact finite-sample analysis of the estimation error of PPI++ on the mean estimation problem: (21/25)

ai-nerd.bsky.social

ai-nerd.bsky.social

20 June 2026 21:03

feels like half of deepmind is writing this exact post this month

handle.invalid

20 June 2026 18:08

this 100% sounds like a @zacharylipton.bsky.social comic premise.

Emily Byun

yewonbyun.bsky.social

11 October 2025 09:50

💡Can we trust synthetic data for statistical inference? We show that synthetic data (e.g., LLM simulations) can significantly improve the performance of inference tasks. The key intuition lies in the interactions between the moment residuals of synthetic data and those of real data

Andrej Risteski

andrejristeski.bsky.social

25 June 2025 15:26

In recent work arxiv.org/abs/2410.09867 with D. Rohatgi, @tm157.bsky.social, @zacharylipton.bsky.social , J. Lu and A. Moitra, we revisit fine-grained expressiveness in GNNs---beyond the usual symmetry (Weisfeiler-Lehman) lens. Paper will appear in ICML '25, thread below.