On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Karchmer, Ari
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917724198797312
author Karchmer, Ari
author_facet Karchmer, Ari
contents Recently, multimodal machine learning has enjoyed huge empirical success (e.g. GPT-4). Motivated to develop theoretical justification for this empirical success, Lu (NeurIPS '23, ALT '24) introduces a theory of multimodal learning, and considers possible \textit{separations} between theoretical models of multimodal and unimodal learning. In particular, Lu (ALT '24) shows a computational separation, which is relevant to \textit{worst-case} instances of the learning task. In this paper, we give a stronger \textit{average-case} computational separation, where for ``typical'' instances of the learning task, unimodal learning is computationally hard, but multimodal learning is easy. We then question how ``natural'' the average-case separation is. Would it be encountered in practice? To this end, we prove that under basic conditions, any given computational separation between average-case unimodal and multimodal learning tasks implies a corresponding cryptographic key agreement protocol. We suggest to interpret this as evidence that very strong \textit{computational} advantages of multimodal learning may arise \textit{infrequently} in practice, since they exist only for the ``pathological'' case of inherently cryptographic distributions. However, this does not apply to possible (super-polynomial) \textit{statistical} advantages.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02254
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
Karchmer, Ari
Machine Learning
Artificial Intelligence
Recently, multimodal machine learning has enjoyed huge empirical success (e.g. GPT-4). Motivated to develop theoretical justification for this empirical success, Lu (NeurIPS '23, ALT '24) introduces a theory of multimodal learning, and considers possible \textit{separations} between theoretical models of multimodal and unimodal learning. In particular, Lu (ALT '24) shows a computational separation, which is relevant to \textit{worst-case} instances of the learning task. In this paper, we give a stronger \textit{average-case} computational separation, where for ``typical'' instances of the learning task, unimodal learning is computationally hard, but multimodal learning is easy. We then question how ``natural'' the average-case separation is. Would it be encountered in practice? To this end, we prove that under basic conditions, any given computational separation between average-case unimodal and multimodal learning tasks implies a corresponding cryptographic key agreement protocol. We suggest to interpret this as evidence that very strong \textit{computational} advantages of multimodal learning may arise \textit{infrequently} in practice, since they exist only for the ``pathological'' case of inherently cryptographic distributions. However, this does not apply to possible (super-polynomial) \textit{statistical} advantages.
title On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.02254