Pith. sign in

REVIEW 4 cited by

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

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 2002.10716 v2 pith:A6Z42HN2 submitted 2020-02-25 cs.LG stat.ML

classification cs.LGstat.ML
keywords errorstandardrobustadversariallinearperturbationspredictortraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Adversarial training augments the training set with perturbations to improve the robust error (over worst-case perturbations), but it often leads to an increase in the standard error (on unperturbed test inputs). Previous explanations for this tradeoff rely on the assumption that no predictor in the hypothesis class has low standard and robust error. In this work, we precisely characterize the effect of augmentation on the standard error in linear regression when the optimal linear predictor has zero standard and robust error. In particular, we show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor. We then prove that the recently proposed robust self-training (RST) estimator improves robust error without sacrificing standard error for noiseless linear regression. Empirically, for neural networks, we find that RST with different adversarial training methods improves both standard and robust error for random and adversarial rotations and adversarial $\ell_\infty$ perturbations in CIFAR-10.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Adversarial Examples Are Not Bugs, They Are Superposition

    cs.LG 2025-08 unverdicted novelty 6.0 of 10

    The paper argues that adversarial examples arise from superposition, and shows that changing superposition changes robustness and vice versa in toy models and ResNet18.

  2. Adversarial Training Improves Generalization Under Distribution Shifts in Bioacoustics

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Output-space adversarial training improved clean-data performance and adversarial robustness of two bird sound classifiers across seven soundscape test sets, and stabilized prototype-based explanations.

  3. When Maximum Entropy Misleads Policy Optimization

    cs.LG 2025-06 reject novelty 6.0 of 10

    Maximum entropy RL can be formally steered into arbitrary suboptimal policies at convergence by adding entropy trap states, while standard RL is unaffected.

  4. Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing

    cs.LG 2025-05 conditional novelty 6.0 of 10

    For binary classification with noisy labels, the paper derives the Bayes-optimal function for combining a model's current predictions with the given labels during retraining, and shows a fitted version improves linear...

Pith tools