DeepAI AI Chat
Log In Sign Up

Malign Overfitting: Interpolation Can Provably Preclude Invariance

by   Yoav Wald, et al.

Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing regularizers are ineffective in the over-parameterized regime, in which classifiers perfectly fit (i.e. interpolate) the training data. This suggests that the phenomenon of “benign overfitting," in which models generalize well despite interpolating, might not favorably extend to settings in which robustness or fairness are desirable. In this work we provide a theoretical justification for these observations. We prove that – even in the simplest of settings – any interpolating learning rule (with arbitrarily small margin) will not satisfy these invariance properties. We then propose and analyze an algorithm that – in the same setting – successfully learns a non-interpolating classifier that is provably invariant. We validate our theoretical observations on simulated data and the Waterbirds dataset.


page 1

page 2

page 3

page 4


Robust Neural Network Classification via Double Regularization

The presence of mislabeled observations in data is a notoriously challen...

A Simple Strategy to Provable Invariance via Orbit Mapping

Many applications require robustness, or ideally invariance, of neural n...

Learning Security Classifiers with Verified Global Robustness Properties

Recent works have proposed methods to train classifiers with local robus...

Interpolation can hurt robust generalization even when there is no noise

Numerous recent works show that overparameterization implicitly reduces ...

On Invariance Penalties for Risk Minimization

The Invariant Risk Minimization (IRM) principle was first proposed by Ar...

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization

Linear classifiers and leaky ReLU networks trained by gradient flow on t...

Unified Adversarial Invariance

We present a unified invariance framework for supervised neural networks...