paper-with-me

홈 › Papers

The Bias-Expressivity Trade-off

2019-11-09 · Julius Lauw, Dominique Macias, Akshay Trikha, Julia Vendemiatti, George D. Montanez

Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on changes in its input. We measure expressivity by using an information-theoretic notion of entropy on algorithm outcome distributions, demonstrating a trade-off between bias and expressivity. To the degree an algorithm is biased is the degree to which it can outperform uniform random sampling, but is also the degree to which is becomes inflexible. We derive bounds relating bias to expressivity, proving the necessary trade-offs inherent in trying to create strongly performing yet flexible algorithms.

📄 PDF Abstract BibTeX arXiv:1911.04964

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Do Quantum Neural Networks have Simplicity Bias?

2024-07-03 · Jessica Pointing

One hypothesis for the success of deep neural networks (DNNs) is that they are highly expressive, which enables them to be applied to many problems, and they have a strong inductive bias towards solutions that are simple…

Inductive Bias

Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability

2021-06-07 · Shangmin Guo, Yi Ren, Kory Mathewson, Simon Kirby 외

Researchers are using deep learning models to explore the emergence of language in various language games, where agents interact and develop an emergent language to solve tasks. We focus on the factors that determine the…

Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability

2021-09-29 · ICLR 2022 4 · Shangmin Guo, Yi Ren, Kory Wallace Mathewson, Simon Kirby 외

Researchers are using deep learning models to explore the emergence of language in various language games, where simulated agents interact and develop an emergent language to solve a task. We focus on factors which deter…

The Transformation Logics

2023-04-19 · Alessandro Ronca

We introduce a new family of temporal logics designed to finely balance the trade-off between expressivity and complexity. Their key feature is the possibility of defining operators of a new kind that we call transformat…

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem

2021-10-19 · Clayton Sanford, Vaggos Chatziafratis

Given a target function $f$, how large must a neural network be in order to approximate $f$? Recent works examine this basic question on neural network \textit{expressivity} from the lens of dynamical systems and provide…