Pith. sign in

REVIEW 2 cited by

Learning with Non-Convex Truncated Losses by SGD

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 1805.07880 v1 pith:L24KRSJC submitted 2018-05-21 cs.LG stat.ML

classification cs.LGstat.ML
keywords learningfunctionslosslossesnoisenon-convextruncateddeep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper, we study a family of objective functions formed by truncating traditional loss functions, which is applicable to both shallow learning and deep learning. Truncating loss functions has potential to be less vulnerable and more robust to large noise in observations that could be adversarial. More importantly, it is a generic technique without assuming the knowledge of noise distribution. To justify non-convex learning with truncated losses, we establish excess risk bounds of empirical risk minimization based on truncated losses for heavy-tailed output, and statistical error of an approximate stationary point found by stochastic gradient descent (SGD) method. Our experiments for shallow and deep learning for regression with outliers, corrupted data and heavy-tailed noise further justify the proposed method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints

    math.OC 2019-08 conditional novelty 6.0 of 10

    A proximally constrained subgradient method finds a nearly stationary point for weakly convex objectives with weakly convex constraints in O(1/epsilon^4) deterministic and O~(1/epsilon^6) stochastic iterations.

  2. Stochastic Optimization for Non-convex Inf-Projection Problems

    cs.LG 2019-08 conditional novelty 5.0 of 10

    The paper provides stochastic algorithms with O(1/epsilon^{4/v}) iteration complexity for finding near-stationary points of non-convex inf-projection objectives, with a variance-regularization application.

Pith tools