6 papers
Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
Dongxuan Zhu, Ly Tran Ho Khanh, Andy Yat-Ming Cheung +2
Language models often default to a narrow set of high-probability outputs, leaving their generation paths homogeneous and prone to mode collapse. Sampling-based strategies inject r…
Test-time Diverse Reasoning by Riemannian Activation Steering
Ly Tran Ho Khanh, Dongxuan Zhu, Man-Chung Yue +1
Best-of- reasoning improves the accuracy of language models in solving complex tasks by sampling multiple candidate solutions and then selecting the best one based on some crite…
A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set
Man-Chung Yue, Yves Rychener, Daniel Kuhn +1
The state-of-the-art methods for estimating high-dimensional covariance matrices all shrink the eigenvalues of the sample covariance matrix towards a data-insensitive shrinkage tar…
A Max-Min-Max Algorithm for Large-Scale Robust Optimization
Kai Tu, Zhi Chen, Man-Chung Yue
Robust optimization (RO) is a powerful paradigm for decision making under uncertainty. Existing algorithms for solving RO, including the reformulation approach and the cutting-plan…
An MILP-Based Solution Scheme for Factored and Robust Factored Markov Decision Processes
Huikang Liu, Wolfram Wiesemann, Man-Chung Yue
Factored Markov decision processes (MDPs) are a prominent paradigm within the artificial intelligence community for modeling and solving large-scale MDPs whose rewards and dynamics…
Coverage-Validity-Aware Algorithmic Recourse
Ngoc Bui, Duy Nguyen, Man-Chung Yue +1
Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency, and ethics of machine learning models. Existing algorithmic recourse approaches o…