Recent works have demonstrated that neural networks exhibit extreme *simplicity bias* (SB). That is, they learn *only the simplest* features to solve a task at hand, even in the presence of other, more robust but more complex features. Due to the lack of a general and rigorous definition of *features*, these works showcase SB on *semi-synthetic* datasets such as Color-MNIST, MNIST-CIFAR where defining features is relatively easier. In this work, we rigorously define as well as thoroughly establish SB for *one hidden layer* neural networks in the infinite width regime. More concretely, (i) we define SB as the network essentially being a function of a low dimensional projection of the inputs (ii) theoretically, we show that when the data is linearly separable, the network primarily depends on only the linearly separable ($1$-dimensional) subspace even in the presence of an arbitrarily large number of other, more complex features which could have led to a significantly more robust classifier, (iii) empirically, we show that models trained on *real* datasets such as Imagenet and Waterbirds-Landbirds indeed depend on a low dimensional projection of the inputs, thereby demonstrating SB on these datasets, iv) finally, we present a natural ensemble approach that encourages diversity in models by training successive models on features not used by earlier models, and demonstrate that it yields models that are significantly more robust to Gaussian noise.

Recent works have demonstrated that neural networks exhibit extreme *simplicity bias* (SB). That is, they learn *only the simplest* features to solve a task at hand, even in the presence of other, more robust but more complex features. Due to the lack of a general and rigorous definition of *features*, these works showcase SB on *semi-synthetic* datasets such as Color-MNIST, MNIST-CIFAR where defining features is relatively easier. In this work, we rigorously define as well as thoroughly establish SB for *one hidden layer* neural networks in the infinite width regime. More concretely, (i) we define SB as the network essentially being a function of a low dimensional projection of the inputs (ii) theoretically, we show that when the data is linearly separable, the network primarily depends on only the linearly separable ( 1 -dimensional) subspace even in the presence of an arbitrarily large number of other, more complex features which could have led to a significantly more robust classifier, (iii) empirically, we show that models trained on *real* datasets such as Imagenet and Waterbirds-Landbirds indeed depend on a low dimensional projection of the inputs, thereby demonstrating SB on these datasets, iv) finally, we present a natural ensemble approach that encourages diversity in models by training successive models on features not used by earlier models, and demonstrate that it yields models that are significantly more robust to Gaussian noise.

Deep generative models can learn to generate realistic-looking images on several natural image datasets, but many of the most effective methods are adversarial methods, which require careful balancing of training between a generator network and a discriminator network. Maximum mean discrepancy networks (MMD-nets) avoid this issue using the kernel trick, but unfortunately they have not on their own been able to match the performance of adversarial training. We present a new method of training MMD-nets, based on learning a mapping of samples from the data and from the model into a lower dimensional space, in which MMD training can be more effective. We call these networks ratio matching MMD networks (RM-MMDnets). We train the mapping to preserve density ratios between the densities over the low-dimensional space and the original space. This ensures that matching the model distribution to the data in the low-dimensional space will also match the original distributions. We show that RM-MMDnets have better performance and better stability than recent adversarial methods for training MMD-nets.

We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance) for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points in the same class are simultaneously near each other and far from points in the other classes. We construct a convex optimization problem whose solution generates such a metric by trying to collapse all examples in the same class to a single point and push examples in other classes infinitely far away. We show that when the metric we learn is used in simple classifiers, it yields substantial improvements over standard alternatives on a variety of problems. We also discuss how the learned metric may be used to obtain a compact low dimensional feature representation of the original input space, allowing more efficient classification with very little reduction in performance.

We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance) for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points in the same class are simultaneously near each other and far from points in the other classes. We construct a convex optimization problem whose solution generates such a metric by trying to collapse all examples in the same class to a single point and push examples in other classes infinitely far away. We show that when the metric we learn is used in simple classifiers, it yields substantial improvements over standard alternatives on a variety of problems. We also discuss how the learned metric may be used to obtain a compact low dimensional feature representation of the original input space, allowing more efficient classification with very little reduction in performance.

We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance)for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points in the same class are simultaneously near each other and far from points in the other classes. We construct a convex optimization problem whose solution generates such a metric by trying to collapse all examples in the same class to a single point and push examples in other classes infinitely far away. We show that when the metric we learn is used in simple classifiers, ityields substantial improvements over standard alternatives on a variety of problems. We also discuss how the learned metric may be used to obtain a compact low dimensional feature representation of the original input space, allowing more efficient classification with very little reduction in performance.

People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a lowlevel, faces severe challenges, including the lack of accurate statistical models for the signals, and their high-dimensionality and varied sampling rates. Previous approaches [6] assumed simple parametric models for the joint distribution which, while tractable, cannot capture the complex signal relationships. We learn the joint distribution of the visual and auditory signals using a nonparametric approach. First, we project the data into a maximally informative, low-dimensional subspace, suitable for density estimation.

People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a lowlevel, faces severe challenges, including the lack of accurate statistical models for the signals, and their high-dimensionality and varied sampling rates. Previous approaches [6] assumed simple parametric models for the joint distribution which, while tractable, cannot capture the complex signal relationships. We learn the joint distribution of the visual and auditory signals using a nonparametric approach. First, we project the data into a maximally informative, low-dimensional subspace, suitable for density estimation.

People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a lowlevel, facessevere challenges, including the lack of accurate statistical models for the signals, and their high-dimensionality and varied sampling rates.Previous approaches [6] assumed simple parametric models for the joint distribution which, while tractable, cannot capture the complex signalrelationships. We learn the joint distribution of the visual and auditory signals using a nonparametric approach. First, we project the data into a maximally informative, low-dimensional subspace, suitable for density estimation. We then model the complicated stochastic relationships betweenthe signals using a nonparametric density estimator.