An Iterative Algorithm for Rescaled Hyperbolic Functions Regression
share
Large language models (LLMs) have numerous real-life applications across various domains, such as natural language translation, sentiment analysis, language modeling, chatbots and conversational agents, creative writing, text classification, summarization, and generation. LLMs have shown great promise in improving the accuracy and efficiency of these tasks, and have the potential to revolutionize the field of natural language processing (NLP) in the years to come. Exponential function based attention unit is a fundamental element in LLMs. Several previous works have studied the convergence of exponential regression and softmax regression. The exponential regression [Li, Song, Zhou 2023] and softmax regression [Deng, Li, Song 2023] can be formulated as follows. Given matrix A ∈ℝ^n × d and vector b ∈ℝ^n, the goal of exponential regression is to solve min_xexp(Ax) - b _2 and the goal of softmax regression is to solve min_x⟨exp(Ax) , 1_n ⟩^-1exp(Ax) - b _2 . In this work, we define a slightly different formulation than softmax regression. min_x ∈ℝ^d u(x) - ⟨ u(x) , 1_n ⟩· b _2 where u(x) ∈{exp(Ax), cosh(Ax) , sinh(Ax) }. We provide an input sparsity time algorithm for this problem. Our algorithm framework is very general and can be applied to functions like cosh() and sinh() as well. Our technique is also general enough to be applied to in-context learning for rescaled softmax regression.
READ FULL TEXT