Search Results for author:
Found 7 papers, 2 papers with code
Number Representations in LLMs: A Computational Parallel to Human Perception
Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones.
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces
This paper investigates whether large language models (LLMs) utilize numerical attributes encoded in a low-dimensional subspace of the embedding space when answering logical comparison questions (e. g., Was Cristiano born before Messi?).
Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging
Recently, an OGD algorithm emerged, employing gradient computation involving prior and most recent examples, a step that effectively reduces algorithmic complexity to $O(T)$, with $T$ being the number of received examples.
Variance Reduced Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory
Specifically, we establish a clear connection between the variance of online gradients and the regret, and construct online gradients using the most recent stratified samples with a limited buffer of size of $s$ representing all past data, which have a complexity of $O(sT)$ and employs $O(\sqrt{T}\log{T})$ random Fourier features for kernel approximation.
Computational Complexity of Sub-Linear Convergent Algorithms
One of these approaches is reducing the gradient variance through adaptive sampling to solve large-scale optimization's empirical risk minimization (ERM) problems.
Pairwise Learning via Stagewise Training in Proximal Setting
Recent research has, however, offered adaptive sample size training for smooth loss functions as a better strategy in terms of convergence and complexity, but without a comprehensive theoretical study.
Investigating a Baseline Of Self Supervised Learning Towards Reducing Labeling Costs For Image Classification
Results show that the pretext process in the self-supervised learning improves the accuracy around 15% in the downstream classification task when compared to the plain supervised learning.
