Pith. sign in

REVIEW 1 cited by

Provable Regret Bounds for Deep Online Learning and Control

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.07807 v3 pith:NC43OTQG submitted 2021-10-15 cs.LG

classification cs.LG
keywords deeplearningonlineoptimizationcontrolregretderivegradient
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The theory of deep learning focuses almost exclusively on supervised learning, non-convex optimization using stochastic gradient descent, and overparametrized neural networks. It is common belief that the optimizer dynamics, network architecture, initialization procedure, and other factors tie together and are all components of its success. This presents theoretical challenges for analyzing state-based and/or online deep learning. Motivated by applications in control, we give a general black-box reduction from deep learning to online convex optimization. This allows us to decouple optimization, regret, expressiveness, and derive agnostic online learning guarantees for fully-connected deep neural networks with ReLU activations. We quantify convergence and regret guarantees for any range of parameters and allow any optimization procedure, such as adaptive gradient methods and second order methods. As an application, we derive provable algorithms for deep control in the online episodic setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Incremental Online Learning of Randomized Neural Network with Forward Regularization

    cs.LG 2024-12 reject novelty 5.0 of 10

    The authors derive incremental online ridge and forward algorithms for edRVFL with batch-stream regret bounds, claiming forward regularization is superior, but the key regret proof contains a false equality.

Pith tools