collaborators

18 papers

cs.LG2026

TREK: Distill to Explore, Reinforce to Refine

Yuanda Xu, Zhengze Zhou, Kayhan Behdin +10

Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution m…

cs.AI2026

Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

Ryan Lucas, Kayhan Behdin, Zhipeng Wang +3

Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression t…

cs.LG2026

Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo

Jelena Markovic-Voronov, Wenhui Zhu, Bo Long +5

We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-l…

cs.LG2026

Sparse Gaussian Graphical Models with Discrete Optimization: Computational and Statistical Perspectives

Kayhan Behdin, Wenyu Chen, Rahul Mazumder

We consider the problem of learning a sparse graph underlying an undirected Gaussian graphical model, a key problem in statistical machine learning. Given samples from a multiv…

stat.ME2026

Sparse PCA: A New Scalable Estimator Based On Integer Programming

Kayhan Behdin, Rahul Mazumder

We consider the Sparse Principal Component Analysis (SPCA) problem under the well-known spiked covariance model. Recent work has shown that the SPCA problem can be reformulated as…

stat.ME2026

Modeling with Categorical Features via Exact Fusion and Sparsity Regularisation

Kayhan Behdin, Riade Benbaki, Peter Radchenko +1

We study the high-dimensional linear regression problem with categorical predictors that have many levels. We propose a new estimation approach, which performs model compression vi…