# Learnability with Time-Sharing Computational Resource Concerns

arXiv: https://arxiv.org/abs/2305.02217 · HTML: https://mlsanity.com/paper/2305.02217/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 7 references that are in the map.
- First posted on arXiv 3 May 2023.

## Builds on (most cited first, 1 of 1)

- [Open-environment Machine Learning](https://mlsanity.com/paper/2206.00423/) (2022)

## Built on by (most cited first, 7 of 7)

- [Representation Learning for Tabular Data: A Comprehensive Survey](https://mlsanity.com/paper/2504.16109/) (2025)
- [Gradient-Variation Online Learning under Generalized Smoothness](https://mlsanity.com/paper/2408.09074/) (2024)
- [Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought](https://mlsanity.com/paper/2402.06918/) (2024)
- [Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching](https://mlsanity.com/paper/2410.10258/) (2024)
- [Optimal Matrix Sketching over Sliding Windows](https://mlsanity.com/paper/2405.07792/) (2024)
- [COURIER: Contrastive User Intention Reconstruction for Large-Scale Visual Recommendation](https://mlsanity.com/paper/2306.05001/) (2023)
- [Harnessing Scalable Transactional Stream Processing for Managing Large Language Models [Vision]](https://mlsanity.com/paper/2307.08225/) (2023)

## Abstract (arXiv)

Conventional theoretical machine learning studies generally assume explicitly or implicitly that there are enough or even infinitely supplied computational resources. In real practice, however, computational resources are usually limited, and the performance of machine learning depends not only on how many data have been received, but also on how many data can be handled subject to computational resources available. Note that most current ``intelligent supercomputing'' facilities work like exclusive operating systems, where a fixed amount of resources are allocated to a machine learning task without adaptive scheduling strategies considering important factors such as the learning performance demands and learning process status. In this article, we introduce the notion of machine learning throughput, define Computational Resource Efficient Learning (CoRE-Learning), and present a theoretical framework that takes into account the influence of computational resources in learning theory. This framework can be naturally applied to stream learning where the incoming data streams can be potentially endless with overwhelming size and it is impractical to assume that all received data can be handled in time. It may also provide a theoretical perspective for the design of intelligent supercomputing operating systems.