activity
20242026
collaborators

6 papers

stat.ML2026

Model-based Bootstrap of Controlled Markov Chains

Ziwei Su, Imon Banerjee, Diego Klabjan

We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history-dependent control policies, a…

math.ST2026

Central Limit Theorems for Transition Probabilities of Controlled Markov Chains

Ziwei Su, Imon Banerjee, Diego Klabjan

We develop a central limit theorem (CLT) for a non-parametric estimator of the transition matrices in controlled Markov chains (CMCs) with finite state-action spaces. Our results e…

cs.LG2026

A Trainable Optimizer

Ruiqi Wang, Diego Klabjan

The concept of learning to optimize involves utilizing a trainable optimization strategy rather than relying on manually defined full gradient estimations such as ADAM. We present…

cs.LG2025

Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context

Taejong Joo, Diego Klabjan

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelli…

stat.ME2024

Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization

Ziwei Su, Diego Klabjan

Stochastic simulation models are generative models that mimic complex systems to help with decision-making. The reliability of these models heavily depends on well-calibrated input…

cs.LG2024

Improving self-training under distribution shifts via anchored confidence with theoretical guarantees

Taejong Joo, Diego Klabjan

Self-training often falls short under distribution shifts due to an increased discrepancy between prediction confidence and actual accuracy. This typically necessitates computation…