NP-EBCIs achieve asymptotic exact coverage for individual effects at logarithmic rates and shorten intervals in simulations compared to isolated treatment.
An introductory guide to Fano’s inequality with appli- cations in statistical estimation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Neural scaling laws are invariant under bijective data transformations and change predictably with information resolution ρ under non-bijective transformations, enabling cross-domain transport of fitted exponents.
A covering-plus-sketching scheme plus f-divergence lower bound characterizes the communication-accuracy tradeoff for sparse aggregation, tight on binary alphabets but with a gap on general alphabets.
CLSR lets LLM agents evolve and route symbolic languages that reduce generated tokens by 3-6x versus chain-of-thought while keeping accuracy on benchmarks.
SCBoost applies spectral residual projection and covariance-regularized weighting to reduce redundancy in boosting, claiming exact residual-energy decomposition and SNR gains under isotropic noise, with gains on ten benchmarks.
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
citing papers explorer
-
Nonparametric Empirical Bayes Confidence Intervals
NP-EBCIs achieve asymptotic exact coverage for individual effects at logarithmic rates and shorten intervals in simulations compared to isolated treatment.
-
On the Invariance and Generality of Neural Scaling Laws
Neural scaling laws are invariant under bijective data transformations and change predictably with information resolution ρ under non-bijective transformations, enabling cross-domain transport of fitted exponents.
-
Lossy Compression for Sparse Aggregation
A covering-plus-sketching scheme plus f-divergence lower bound characterizes the communication-accuracy tradeoff for sparse aggregation, tight on binary alphabets but with a gap on general alphabets.
-
When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
CLSR lets LLM agents evolve and route symbolic languages that reduce generated tokens by 3-6x versus chain-of-thought while keeping accuracy on benchmarks.
-
Reducing Learner Redundancy in Boosting via Residual Orthogonalization
SCBoost applies spectral residual projection and covariance-regularized weighting to reduce redundancy in boosting, claiming exact residual-energy decomposition and SNR gains under isotropic noise, with gains on ten benchmarks.
-
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.