arXiv subjects

Ethan Kim

Publications and source records attributed to Ethan Kim.

4 recordsLinked to original sources

arXiv2024

An Analysis of a 2x2 Keyfitz-Kranzer Type Balance System with Varying Generalized Chaplygin Gas

We consider a system of two balance laws of Keyfitz-Kranzer type with varying generalized Chaplygin gas, which exhibits negative pressure and is a product of a function of time and the inverse of a power of the density. The Chaplygin gas is a fluid designed to accommodate measurements for the early universe and late-time universal expansion while obeying the pressure-density-time relation. We produce an explanation and description of the non-self-similar Riemann solutions, including the non-classical singular solutions. We also find that due to a direct dependence on time, a change in the regions allowing for combinations of classical and non-classical singular solutions occurs, therefore a Riemann solution can have different solutions over several time intervals. Our findings are confirmed numerically using the local Lax-Friederichs scheme.

math.AP↗

arXiv2023

Differentiable Entailment for Parameter Efficient Few Shot Learning

Few-shot learning allows pre-trained language models to adapt to downstream tasks while using a limited number of training examples. However, practical applications are limited when all model parameters must be optimized. In this work we apply a new technique for parameter efficient few shot learning while adopting a strict definition of parameter efficiency. Our training method combines 1) intermediate training by reformulating natural language tasks as entailment tasks \cite{wang_entailment_2021} and 2) differentiable optimization of template and label tokens \cite{zhang_differentiable_2021}. We quantify the tradeoff between parameter efficiency and performance in the few-shot regime and propose a simple model agnostic approach that can be extended to any task By achieving competitive performance while only optimizing 3\% of a model's parameters and allowing for batched inference, we allow for more efficient practical deployment of models.

cs.CL↗

arXiv2022

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

cs.CL↗

arXiv2006

On Bus Graph Realizability

In this paper, we consider the following graph embedding problem: Given a bipartite graph G = (V1; V2;E), where the maximum degree of vertices in V2 is 4, can G be embedded on a two dimensional grid such that each vertex in V1 is drawn as a line segment along a grid line, each vertex in V2 is drawn as a point at a grid point, and each edge e = (u; v) for some u 2 V1 and v 2 V2 is drawn as a line segment connecting u and v, perpendicular to the line segment for u? We show that this problem is NP-complete, and sketch how our proof techniques can be used to show the hardness of several other related problems.

cs.CG↗