Provably Strict Generalisation Benefit for Invariance in Kernel Methods
Dez 6, 2021
Sprecher:innen
Bryn Elesedy
Speaker · 0 followers
Über
It is a commonly held belief that enforcing invariance improves generalisation. Although this approach enjoys widespread popularity, it is only very recently that a rigorous theoretical demonstration of this benefit has been established. In this work we build on the function space perspective of Elesedy and Zaidi [8] to derive a strictly non-zero generalisation benefit of incorporating invariance in kernel ridge regression when the target is invariant to the action of a compact group. We study invariance enforced by feature averaging and find that generalisation is governed by a notion of effective dimension that arises from the interplay between the kernel and the group. In building towards this result, we find that the action of the group induces an orthogonal decomposition of both the reproducing kernel Hilbert space and its kernel, which may be of interest in its own right.It is a commonly held belief that enforcing invariance improves generalisation. Although this approach enjoys widespread popularity, it is only very recently that a rigorous theoretical demonstration of this benefit has been established. In this work we build on the function space perspective of Elesedy and Zaidi [8] to derive a strictly non-zero generalisation benefit of incorporating invariance in kernel ridge regression when the target is invariant to the action of a compact group. We study i…
Organisator
NeurIPS 2021
Account · 1.9k followers
Über NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
The Art of Gaussian Processes: Classical and Contemporary
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models
Watch later
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%
InfiniteForm: A synthetic, minimal bias dataset for fitness applications
Watch later
Andrew Weitz, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Multi-Agent Reinforcement Learning in Stochastic Networked Systems
Watch later
Yiheng Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A New sPHENIX Heavy Quark Trigger Algorithm Based on Graph Neutral Networks
Watch later
Yimin Zhu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%