Multiple instance regression (MIR) was introduced by Ray and Page (2001) as an analogue of multiple instance learning (MIL) in which we are given bags of feature-vectors (instances) and for each bag there is a bag-label which matches the label of one (unknown) primary instance from that bag. The goal is to compute a hypothesis regressor consistent with the underlying instance-labels. A natural approach is to find the best primary instance assignment and regressor optimizing the mse loss on the bags though no formal generalization guarantees were known. Our work is the first to prove generalization error bounds for MIR when the bags are drawn i.i.d. at random. Essentially, with high probability any MIR regressor with low error on sampled bags also has low error on the underlying instance-label distribution. We next study the complexity of linear regression on MIR bags, shown to be NP-hard in general by Ray and Page (2001), who however left open the possibility of arbitrarily good approximations. Significantly strengthening previous work, we prove a strong inapproximability bound: even if there exists zero bag-loss MIR linear regressor on a collection of $2$-sized bags with labels in $[-1,1]$, it is NP-hard to find an MIR linear regressor with bag-loss $< C$ for some absolute constant $C > 0$. Our work also proposes a model training method for MIR based on a novel weighted assignment loss, geared towards handling overlapping bags which have not received much attention previously. We conduct empirical evaluations on synthetic and real-world datasets showing that our method outperforms the baseline MIR methods.

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model can query a human collaborator for the label to some concepts. We develop an interaction policy that, at prediction time, chooses which concepts to request a label for so as to maximally improve the final prediction. We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms static approaches as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10% with only 5 interactions over competitive baselines on the Caltech-UCSD Birds, CheXpert and OAI datasets.

Reliable outlier detection is critical for real-world deployment of deep learning models. Although extensively studied, likelihoods produced by deep generative models have been largely dismissed as being impractical for outlier detection. First, deep generative model likelihoods are readily biased by low-level input statistics. Second, many recent solutions for correcting these biases are computationally expensive, or do not generalize well to complex, natural datasets. Here, we explore outlier detection with a state-of-the-art deep autoregressive model: PixelCNN++. We show that biases in PixelCNN++ likelihoods arise primarily from predictions based on local dependencies. We propose two families of bijective transformations -- ``stirring'' and ``shaking'' -- which ameliorate low-level biases and isolate the contribution of long-range dependencies to PixelCNN++ likelihoods. These transformations are inexpensive and readily computed at evaluation time. We test our approaches extensively with five grayscale and six natural image datasets and show that they achieve or exceed state-of-the-art outlier detection, particularly on datasets with complex, natural images. We also show that our solutions work well with other types of generative models (generative flows and variational autoencoders) and that their efficacy is governed by each model's reliance on local dependencies. In sum, lightweight remedies suffice to achieve robust outlier detection on image data with deep generative models.

Deep networks often make confident, yet, incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that DGM likelihoods are unreliable and can be easily biased by simple transformations to input data. Here, we examine outlier detection with variational autoencoders (VAEs), among the simplest of DGMs. We propose novel analytical and algorithmic approaches to ameliorate key biases with VAE likelihoods. Our bias corrections are sample-specific, computationally inexpensive, and readily computed for various decoder visible distributions. Next, we show that a well-known image pre-processing technique – contrast stretching – extends the effectiveness of bias correction to further improve outlier detection. Our approach achieves state-of-the-art accuracies with nine grayscale and natural image datasets, and demonstrates significant advantages – both with speed and performance – over four recent, competing approaches. In summary, lightweight remedies suffice to achieve robust outlier detection with VAEs.11Code is available at https://github.com/google-research/google-research/tree/master/vae_ood.

Technical support problems are often long and complex.They typically contain user descriptions of the problem, the setup, and steps for attempted resolution.Often they also contain various non-natural language text elements like outputs of commands, snippets of code, error messages or stack traces.These elements contain potentially crucial information for problem resolution.However, they cannot be correctly parsed by tools designed for natural language.In this paper, we address the problem of segmentation for technical support questions.We formulate the problem as a sequence labelling task, and study the performance of state of the art approaches.We compare this against an intuitive contextual sentence-level classification baseline, and a state of the art supervised text-segmentation approach.We also introduce a novel component of combining contextual embeddings from multiple language models pre-trained on different data sources, which achieves a marked improvement over using embeddings from a single pre-trained language model.Finally, we also demonstrate the usefulness of such segmentation with improvements on the downstream task of answer retrieval.