The spectral weak-recovery threshold for linearized AMP in the multi-view spiked Wigner model is SNR(λ,B)=1, where SNR is the largest eigenvalue of Diag(√λ)(B⊙B)Diag(√λ), and this coincides with the information-theoretic threshold for a broad class of spike priors.
Econometrica , volume=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 7roles
method 1polarities
use method 1representative citing papers
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
Agent's optimization in unique-contract principal-agent problem with adverse selection is recast as stochastic target problem, enabling principal's objective as stochastic optimal control with partial information and state constraints.
Public messaging weakly dominates private messaging for implementing collective project decisions and is strictly dominant in linear-payoff settings with two conflicting allies.
Pricing, matching, and bundling act as complementary levers that platforms can adjust to balance their own profitability against overall market welfare in equilibrium.
citing papers explorer
-
Sharp Spectral Thresholds for Multi-View Spiked Wigner Models
The spectral weak-recovery threshold for linearized AMP in the multi-view spiked Wigner model is SNR(λ,B)=1, where SNR is the largest eigenvalue of Diag(√λ)(B⊙B)Diag(√λ), and this coincides with the information-theoretic threshold for a broad class of spike priors.
-
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
-
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
-
Principal-agent problems with adverse selection: A stochastic target problem formulation
Agent's optimization in unique-contract principal-agent problem with adverse selection is recast as stochastic target problem, enabling principal's objective as stochastic optimal control with partial information and state constraints.
-
Going Public: Communication in Collective Decisions
Public messaging weakly dominates private messaging for implementing collective project decisions and is strictly dominant in linear-payoff settings with two conflicting allies.
-
Pricing, Matching, and Bundling: an Equilibrium Analysis of Online Platforms
Pricing, matching, and bundling act as complementary levers that platforms can adjust to balance their own profitability against overall market welfare in equilibrium.
- Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming