Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Strong inductive biases provably prevent harmless interpolation

Michael Aerni · Marco Milanta · Konstantin Donhauser · Fanny Yang

MH1-2-3-4 #138

Keywords: [ deep learning theory ] [ high-dimensional statistics ] [ non-parametric regression ] [ benign overfitting ] [ generalization bounds ] [ Theory ]


Abstract:

Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield small test error despite interpolating noise — a phenomenon often called "benign overfitting" or "harmless interpolation". This paper argues that the degree to which interpolation is harmless hinges upon the strength of an estimator's inductive bias, i.e., how heavily the estimator favors solutions with a certain structure: while strong inductive biases prevent harmless interpolation, weak inductive biases can even require fitting noise to generalize well. Our main theoretical result establishes tight non-asymptotic bounds for high-dimensional kernel regression that reflect this phenomenon for convolutional kernels, where the filter size regulates the strength of the inductive bias. We further provide empirical evidence of the same behavior for deep neural networks with varying filter sizes and rotational invariance.

Chat is not available.