We have 9 of 35 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions and negotiations with private valuations. We introduce unilateral prescriptive concentrability and show that asymmetric information can change offline coverage through...
This paper develops a machine learning approach for training such agents to act effectively as sellers in a multi-item bargaining environment, where a seller concurrently negotiates a catalog of substitutable assets across a pool of independent buyers.
We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-contingent payment vector, and the agent's best response can make expected profit discontinuous in those payments. For every fixed number $m\ge2$ of outcomes, the minima...
Coupled Calibration and Learning (CCL) is proposed, an LLM distillation algorithm that couples teacher calibration with student updates through token-level branching, using reward feedback only on source questions.
Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which they approximate the maximum Bellman operator by its softmax correspondence, and a debiased estimator is proposed through the Neyman orthogonality and established its asymptotic normality under diverging horizons.
The result shows that standard double machine learning can overstate the intrinsic difficulty of target estimation and provides a target-specific principle for learner selection: approximation error and stochastic complexity must be jointly balanced across the two nuisance learners rather than optimized separately.
A score-whitening method that equalizes local Fisher information and restores stable inference at the optimal sample-complexity scale is introduced that provides a principled framework for uncertainty quantification in LLM evaluation and more broadly for inference on low-rank structures from pairwise data.
The framework separates optimizer design into gradient prediction and online preconditioner selection, providing a principled perspective on how adaptive optimization methods may be understood through static regret and applied in nonconvex optimization.
This work identifies narrow-support imitation as a source of policy collapse in LLM decision-making and suggests that preserving action support during SFT is important for maintaining exploratory behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
