June 6, 2024, 4:42 a.m. | Yifei Wang, Sungyoon Kim, Paul Chu, Indu Subramaniam, Mert Pilanci

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.02806v1 Announce Type: new
Abstract: We introduce randomized algorithms to Clifford's Geometric Algebra, generalizing randomized linear algebra to hypercomplex vector spaces. This novel approach has many implications in machine learning, including training neural networks to global optimality via convex optimization. Additionally, we consider fine-tuning large language model (LLM) embeddings as a key application area, exploring the intersection of geometric algebra and modern AI techniques. In particular, we conduct a comparative analysis of the robustness of transfer learning via embeddings, such …

abstract algebra algorithms arxiv cs.lg embeddings fine-tuning global key language language model large language large language model linear linear algebra llm machine machine learning math.oc networks neural networks novel optimization spaces stat.ml training type vector via

Senior Data Engineer

@ Displate | Warsaw

Solution Architect

@ Philips | Bothell - B2 - Bothell 22050

Senior Product Development Engineer - Datacenter Products

@ NVIDIA | US, CA, Santa Clara

Systems Engineer - 2nd Shift (Onsite)

@ RTX | PW715: Asheville Site W Asheville Greenfield Site TBD , Asheville, NC, 28803 USA

System Test Engineers (HW & SW)

@ Novanta | Barcelona, Spain

Senior Solutions Architect, Energy

@ NVIDIA | US, TX, Remote