5 papers
Effective Quantization of Muon Optimizer States
Aman Gupta, Rafael Celente, Abhishek Shivanna +7
The Muon optimizer, based on matrix orthogonalization, has recently shown faster convergence and better computational efficiency over AdamW in LLM pre-training. However, the memory…
AlphaPO: Reward Shape Matters for LLM Alignment
Aman Gupta, Shao Tang, Qingquan Song +10
Reinforcement Learning with Human Feedback (RLHF) and its variants have made huge strides toward the effective alignment of large language models (LLMs) to follow instructions and…
LiMAML: Personalization of Deep Recommender Models via Meta Learning
Ruofan Wang, Prakruthi Prabhakar, Gaurav Srivastava +10
In the realm of recommender systems, the ubiquitous adoption of deep neural networks has emerged as a dominant paradigm for modeling diverse business objectives. As user bases cont…
LiRank: Industrial Large Scale Ranking Models at LinkedIn
Fedor Borisyuk, Mingzhou Zhou, Qingquan Song +31
We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. We unveil several modelin…
A Precise Characterization of SGD Stability Using Loss Surface Geometry
Gregory Dexter, Borja Ocejo, Sathiya Keerthi +3
Stochastic Gradient Descent (SGD) stands as a cornerstone optimization algorithm with proven real-world empirical successes but relatively limited theoretical understanding. Recent…