Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments. The success of IRM requires an important assumption: the underlying causal mechanisms/features remain invariant across environments. When not satisfied, we show that IRM can over-constrain the predictor and to remedy this, we propose a relaxation via partial invariance. In this work, we theoretically highlight the sub-optimality of IRM and then demonstrate how learning from a partition of training domains can help improve invariant models. Several experiments, conducted both in linear settings as well as with deep neural networks on tasks over both language and image data, allow us to verify our conclusions.

Social persuasion to influence the actions, beliefs, and behaviors of individuals, embedded in a social network, has been widely studied. It has been applied to marketing, healthcare, sustainability, political campaigns, and public policy. Traditionally, there has been a separation between physical (offline) and cyber (online) worlds. While persuasion methods in the physical world focused on strong interpersonal trust and design principles, persuasion methods in the online world were rich on data-driven analysis and algorithms. Recent trends including Internet of Things, “big data,” and smartphone adoption point to the blurring divide between the cyber world and the physical world in the following ways. Fine grained data about each individual's location, situation, social ties, and actions are collected and merged from different sources. The messages for persuasion can be transmitted through both worlds at suitable times and places. The impact of persuasion on each individual is measurable. Hence, we posit that the social persuasion will soon be able to span seamlessly across these worlds and will be able to employ computationally and empirically rigorous methods to understand and intervene in both cyber and physical worlds. Several early examples indicate that this will impact the fundamental facets of persuasion including who, how, where, and when, and pave way for multiple opportunities as well as research challenges.

We consider a network quantizer design setting where agents must balance fidelity in representing their local source distributions against their ability to successfully communicate with other connected agents. By casting the problem as a network game, we show existence of Nash equilibrium quantizer designs. For any agent, under Nash equilibrium, the word representing a given partition region is the conditional expectation of the mixture of local and social source probability distributions within the region. Further, the network may converge to equilibrium through a distributed version of the Lloyd-Max algorithm. In contrast to traditional results in the evolution of language, we find several vocabularies may coexist in the Nash equilibrium, with each individual having exactly one of these vocabularies. The overlap between vocabularies is high for individuals that communicate frequently and have similar local sources. Finally, we argue error in translation along a chain of communication does not grow if and only if the chain consists of agents with shared vocabulary.

In this paper, we develop a novel real-time, interactive, automatic multimodal exploratory environment that dynamically adapts the media presented, to user context. There are two key contributions of this paper – (a) development of multimodal user-context model and (b) modeling the dynamics of the presentation to maximize coherence. We develop a novel user-context model comprising interests, media history, interaction behavior and tasks, that evolves based on the specific interaction. We also develop novel metrics between media elements and the user context. The presentation environment dynamically adapts to the current user context. We develop an optimal media selection and display framework that maximizes coherence, while constrained by the user-context, user goals and the structure of the knowledge in the exploratory environment. The experimental results indicate that the system performs well. The results also show that user-context models significantly improve presentation coherence.

A video segmentation scheme using stabilized inverse diffusion equations is proposed. The scheme is based on the non-linear scale-space analysis of video lattice. Non-linear diffusion and especially stabilized inverse diffusion is a very robust method for image segmentation. In this paper the two-dimensional diffusion process has been extended to three dimensions. The segmentation scheme is based on this extended process. Also, a progressive scale-space evolution of the image sequence is proposed that reduces the memory requirements as well as solves the region correspondence problem. Finally, segmentation results for two image sequences are shown.