TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
Probability inequalities for sums of bounded random variables.Journal of the American statistical association, 58(301):13–30
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Subsampling techniques enable uncoordinated data reuse while keeping the expected variance of Type I error counts close to the independent case, outperforming data splitting in scaling with the number of tests.
LiBaGS scores and selects synthetic data near decision boundaries using proximity, uncertainty, density, and validity, with boundary-gap allocation and marginal stopping to improve training accuracy.
A quantum adjacency state on 2 log N qubits plus ancilla enables subgraph count estimation via m-fold tensor product measurements, producing quantum logspace algorithms for motif counting.
Value mirror descent integrates mirror descent into value iteration for discounted MDPs, delivering near-optimal sample complexity of order |S||A|(1-γ)^{-3}ε^{-2} for general convex regularizers and bounded Bregman divergence between generated and optimal policies.
citing papers explorer
-
TabQL: In-Context Q-Learning with Tabular Foundation Models
TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
-
Data Reuse and the Long Shadow of Error: Splitting, Subsampling, and Prospectively Managing Inferential Errors
Subsampling techniques enable uncoordinated data reuse while keeping the expected variance of Type I error counts close to the independent case, outperforming data splitting in scaling with the number of tests.
-
LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection
LiBaGS scores and selects synthetic data near decision boundaries using proximity, uncertainty, density, and validity, with boundary-gap allocation and marginal stopping to improve training accuracy.
-
Quantum embedding of graphs for subgraph counting
A quantum adjacency state on 2 log N qubits plus ancilla enables subgraph count estimation via m-fold tensor product measurements, producing quantum logspace algorithms for motif counting.
-
Value Mirror Descent for Reinforcement Learning
Value mirror descent integrates mirror descent into value iteration for discounted MDPs, delivering near-optimal sample complexity of order |S||A|(1-γ)^{-3}ε^{-2} for general convex regularizers and bounded Bregman divergence between generated and optimal policies.