Pith. sign in

REVIEW

Improving the convergence of SGD through adaptive batch sizes

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 1910.08222 v4 pith:O6QLXAO7 submitted 2019-10-18 cs.LG math.OCstat.ML

classification cs.LGmath.OCstat.ML
keywords gradientmodelbatchcomputationlossmethodrequiretraining
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Mini-batch stochastic gradient descent (SGD) and variants thereof approximate the objective function's gradient with a small number of training examples, aka the batch size. Small batch sizes require little computation for each model update but can yield high-variance gradient estimates, which poses some challenges for optimization. Conversely, large batches require more computation but can yield higher precision gradient estimates. This work presents a method to adapt the batch size to the model's training loss. For various function classes, we show that our method requires the same order of model updates as gradient descent while requiring the same order of gradient computations as SGD. This method requires evaluating the model's loss on the entire dataset every model update. However, the required computation is greatly reduced by approximating the training loss. We provide experiments that illustrate our methods require fewer model updates without increasing the total amount of computation.

Discussion (0). Continue with ORCID to comment.

Pith tools