We study causal, low-latency, sequential video compression when the output is subjected to both a mean squared-error (MSE) distortion loss as well as a perception loss to target realism. Motivated by prior approaches, we consider two different perception loss functions (PLFs). The first, PLF-JD, considers the joint distribution (JD) of all the video frames up to the current one, while the second metric, PLF-FMD, considers the framewise marginal distributions (FMD) between the source and reconstruction. Using information theoretic analysis and deep-learning based experiments, we demonstrate that the choice of PLF can have a significant effect on the reconstruction, especially at low-bit rates. In particular, while the reconstruction based on PLF-JD can better preserve the temporal correlation across frames, it also imposes a significant penalty in distortion compared to PLF-FMD and further makes it more difficult to recover from errors made in the earlier output frames. Although the choice of PLF decisively affects reconstruction quality, we also demonstrate that it may not be essential to commit to a particular PLF during encoding and the choice of PLF can be delegated to the decoder. In particular, encoded representations generated by training a system to minimize the MSE (without requiring either PLF) can be {\em near universal} and can generate close to optimal reconstructions for either choice of PLF at the decoder. We validate our results using (one-shot) information-theoretic analysis, detailed study of the rate-distortion-perception tradeoff of the Gauss-Markov source model as well as deep-learning based experiments on moving MNIST and KTH datasets.

We study causal, low-latency, sequential video compression when the output is subjected to both a mean squared-error (MSE) distortion loss as well as a perception loss to target realism. Motivated by prior approaches, we consider two different perception loss functions (PLFs). The first, PLF-JD, considers the joint distribution (JD) of all the video frames up to the current one, while the second metric, PLF-FMD, considers the framewise marginal distributions (FMD) between the source and reconstruction. Using information theoretic analysis and deep-learning based experiments, we demonstrate that the choice of PLF can have a significant effect on the reconstruction, especially at low-bit rates. In particular, while the reconstruction based on PLF-JD can better preserve the temporal correlation across frames, it also imposes a significant penalty in distortion compared to PLF-FMD and further makes it more difficult to recover from errors made in the earlier output frames.

Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of noisy, user-written rules and other heuristic labelers. Existing frameworks make the restrictive assumption that labelers output a single class label. Enabling users to create partial labelers that output subsets of possible class labels would greatly expand the expressivity of programmatic weak supervision. We introduce this capability by defining a probabilistic generative model that can estimate the underlying accuracies of multiple noisy partial labelers without ground truth labels. We prove that this class of models is generically identifiable up to label swapping under mild conditions. We also show how to scale up learning to 100k examples in one minute, a 300X speed up compared to a naive implementation. We evaluate our framework on three text classification and six object classification tasks. On text tasks, adding partial labels increases average accuracy by 9.6 percentage points. On image tasks, we show that partial labels allow us to approach some zero-shot object classification problems with programmatic weak supervision by using class attributes as partial labelers. Our framework is able to achieve accuracy comparable to recent embedding-based zero-shot learning methods using only pre-trained attribute detectors

Training-serving skew: The offline numbers may look great, but what if your model will be evaluated on a different or broader set of examples than those found in the training set? This phenomenon, more generally referred to as "dataset shift" or "distribution shift", happens all the time in real-world situations. Models are trained on a curated set of examples, or clicks on top-ranked recommendations, or a specific geographical region, and then applied to every user or use case. Curiosities and anomalies in your training and testing data become genuine and sustained loss patterns. Bad individual errors: Models are often judged by their worst behavior --- a single egregious outcome can damage the faith that important stakeholders have in the model and even cause serious reputational harm to your business or institution.

The combination of argumentation and probability paves the way to new accounts of qualitative and quantitative uncertainty, thereby offering new theoretical and applicative opportunities. Due to a variety of interests, probabilistic argumentation is approached in the literature with different frameworks, pertaining to structured and abstract argumentation, and with respect to diverse types of uncertainty, in particular the uncertainty on the credibility of the premises, the uncertainty about which arguments to consider, and the uncertainty on the acceptance status of arguments or statements. Towards a general framework for probabilistic argumentation, we investigate a labelling-oriented framework encompassing a basic setting for rule-based argumentation and its (semi-) abstract account, along with diverse types of uncertainty. Our framework provides a systematic treatment of various kinds of uncertainty and of their relationships and allows us to retrieve (by derivation) multiple statements (sometimes assumed) or results from the literature.

Another big part of the food supply comes from ranches and farms that raise and slaughter various livestock. While ranching is sometimes bundled with agriculture, I discussed farming in Big Data in Agriculture, so we'll focus on ranching this time around. Somewhat surprising is that big data usage in ranching appears more limited than in farming. That said, there are a number of novel uses of technology and data in animal husbandry. At a high level, the goals of ranching and farming are the same as any business: increase yields and lower costs. Production maximization has long played a role in large operations.

Another big part of the food supply comes from ranches and farms that raise and slaughter various livestock. While ranching is sometimes bundled with agriculture, I discussed farming in Big Data in Agriculture, so we'll focus on ranching this time around. Somewhat surprising is that big data usage in ranching appears more limited than in farming. That said, there are a number of novel uses of technology and data in animal husbandry. At a high level, the goals of ranching and farming are the same as any business: increase yields and lower costs.

Another big part of the food supply comes from ranches and farms that raise and slaughter various livestock. While ranching is sometimes bundled with agriculture, I discussed farming in Big Data in Agriculture, so we'll focus on ranching this time around. Somewhat surprising is that big data usage in ranching appears more limited than in farming. That said, there are a number of novel uses of technology and data in animal husbandry. At a high level, the goals of ranching and farming are the same as any business: increase yields and lower costs. Production maximization has long played a role in large operations.