Taylor Learning
Empirical risk minimization stands behind most optimization in supervised machine learning. Under this scheme, labeled data is used to approximate an expected cost (risk), and a learning algorithm updates model-defining parameters in search of an empirical risk minimizer, with the aim of thereby approximately minimizing expected cost. Parameter update is often done by some sort of gradient descent. In this paper, we introduce a learning algorithm to construct models for real analytic functions using neither gradient descent nor empirical risk minimization. Observing that such functions are defined by local information, we situate familiar Taylor approximation methods in the context of sampling data from a distribution, and prove a nonuniform learning result.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Kernelized Taylor Diagram
This paper presents the kernelized Taylor diagram, a graphical framework for visualizing similarities between data populations. The kernelized Taylor diagram builds on the widely used Taylor diagram, which is used to vis…
Data VisualizationTaylor saves for later: disentanglement for video prediction using Taylor representation
Video prediction is a challenging task with wide application prospects in meteorology and robot systems. Existing works fail to trade off short-term and long-term prediction performances and extract robust latent dynamic…
DisentanglementPredictionVideo PredictionTaylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
Ensuring the security of released large language models (LLMs) poses a significant dilemma, as existing mechanisms either compromise ownership rights or raise data privacy concerns. To address this dilemma, we introduce …
Taylor's power law: before and after 50 years of scientific scrutiny
Taylor's power law is one of the mostly widely known empirical patterns in ecology discovered in the 20th century. It states that the variance of species population density scales as a power-law function of the mean popu…
Taylor TD-learning
Many reinforcement learning approaches rely on temporal-difference (TD) learning to learn a critic. However, TD-learning updates can be high variance. Here, we introduce a model-based RL framework, Taylor TD, which reduc…