RAIC unifies uniform recovery of structured signals from nonlinear observations via PGD, yielding error rates comparable to nonuniform guarantees up to log factors in sparse and 1-bit settings.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
S2MAM is a new semi-supervised model that uses bilevel optimization to automatically identify informative variables, update similarity matrices, and provide interpretable predictions with theoretical guarantees.
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
The paper introduces the Construct Validity Protocol to validate semantic embeddings for social constructs and proposes Counterfactual Neutralization using LLMs to reduce confounding.
Covariance-aware ridge and combined l1-l2 regularizers for neural networks yield better predictive performance and complexity control than standard penalties in simulations and applications to cooling-load prediction and leukemia classification.
Derives homogeneous n-capture element abundances for GBSv3 sample via iSpec spectral analysis and clustering for line selection, yielding measurements in agreement with literature.
citing papers explorer
-
Robust Uniform Recovery of Structured Signals from Nonlinear Observations
RAIC unifies uniform recovery of structured signals from nonlinear observations via PGD, yielding error rates comparable to nonuniform guarantees up to log factors in sparse and 1-bit settings.
-
Language Models as Knowledge Bases?
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
-
S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection
S2MAM is a new semi-supervised model that uses bilevel optimization to automatically identify informative variables, update similarity matrices, and provide interpretable predictions with theoretical guarantees.
-
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
-
The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
The paper introduces the Construct Validity Protocol to validate semantic embeddings for social constructs and proposes Counterfactual Neutralization using LLMs to reduce confounding.
-
Adaptive Norm-Based Regularization for Neural Networks
Covariance-aware ridge and combined l1-l2 regularizers for neural networks yield better predictive performance and complexity control than standard penalties in simulations and applications to cooling-load prediction and leukemia classification.
-
Gaia FGK benchmark stars: abundances of \textit{n}-capture elements of the third version
Derives homogeneous n-capture element abundances for GBSv3 sample via iSpec spectral analysis and clustering for line selection, yielding measurements in agreement with literature.