Search Results for author:
Found 6 papers, 1 papers with code
High Dimensional Structured Superposition Models
High dimensional superposition models characterize observations using parameters which can be written as a sum of multiple component parameters, each with its own structure, e. g., sum of low rank and sparse matrices, sum of sparse and rotated sparse vectors, etc.
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
(2) how can we characterize the stochastic optimization dynamics of SGD with fixed and adaptive step sizes and diagonal pre-conditioning based on the first and second moments of SGs?
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
We also discuss stochastic process based forms of J-L, RIP, and sketching, to illustrate the generality of the results.
Incremental user embedding modeling for personalized text classification
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, and education.
An Evaluation on Large Language Model Outputs: Discourse and Memorization
We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs).
