An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Stochastic integer optimization has sample complexity that matches, undercuts, or exceeds the continuous case based on objective structure, with new tight bounds for nonconvex continuous problems.
POSCMs extend structural causal models to latent contexts that co-determine both graph structure and mechanisms, supported by an identifiability theory and validation in a retina simulator.
In Arrow-Debreu economies with multiplex network externalities, competitive markets satisfy the First and Second Welfare Theorems under regularity or identical layer structures; Lindahl equilibria correct remaining inefficiencies via personalized prices.
Generalized Rank Regression extends rank methods to non-monotonic scores, derives Bahadur representation and asymptotic normality, proposes a two-stage sub-gradient algorithm, and shows variance equivalence to composite quantile regression.
citing papers explorer
-
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
-
Sample Complexity of Stochastic Optimization with Integer Variables
Stochastic integer optimization has sample complexity that matches, undercuts, or exceeds the continuous case based on objective structure, with new tight bounds for nonconvex continuous problems.
-
Partially Observed Structural Causal Models
POSCMs extend structural causal models to latent contexts that co-determine both graph structure and mechanisms, supported by an identifiability theory and validation in a retina simulator.
-
When Do Markets Work? Multiplex Networks and Efficiency
In Arrow-Debreu economies with multiplex network externalities, competitive markets satisfy the First and Second Welfare Theorems under regularity or identical layer structures; Lindahl equilibria correct remaining inefficiencies via personalized prices.
-
Generalized Rank Regression
Generalized Rank Regression extends rank methods to non-monotonic scores, derives Bahadur representation and asymptotic normality, proposes a two-stage sub-gradient algorithm, and shows variance equivalence to composite quantile regression.