9 accepted papers
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best train- ing recipes for reasoning since state-of-the-art models often rely on proprietary datasets with little to no public information available. To…
Matrix completion plays an important role in machine learning and signal processing, with applications ranging from recommender systems to image inpainting. Many approaches have been considered to solve the problem and some offer computationally efficient solutions. In particular, a highly-efficient…
Joint blind source separation (JBSS) is a powerful framework for extracting latent sources from multiple datasets while keeping their coherence across multiple linked datasets. Algorithms for JBSS, while offering the capability of improved estimation performance, often incur high computational compl…
Low-rank matrix completion, the process of estimating a low-rank matrix from a small subset of its entries, has many applications including collaborative filtering and system identification. Many algorithms have been considered to address this problem. Coordinate descent has been previously proposed…
Subgroup identification is a fundamental step in precision medicine. Recent research applying data-driven methods such as independent component/vector analysis to multi-subject functional magnetic resonance imaging (fMRI) data has effectively revealed meaningful subgroups. These methods typically fo…
Modern recommender systems perform large-scale retrieval by embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the re…
Factorization-based gradient descent is a scalable and efficient algorithm for solving low-rank matrix completion. Recent progress in structured non-convex optimization has offered global convergence guarantees for gradient descent under certain statistical assumptions on the low-rank matrix and the…
This paper introduces the use of adaptive restart to accelerate iterative hard thresholding (IHT) for low-rank matrix completion. First, we analyze the local convergence of accelerated IHT in the non-convex setting of matrix completion problem (MCP). We prove the linear convergence rate of the accel…
We present a momentum-based accelerated iterative hard thresholding (IHT) for low-rank matrix completion. We analyze the convergence of the proposed Heavy Ball (HB) accelerated IHT near the solution and provide optimal step size parameters that guarantee the fastest rate of convergence. Since the op…