In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains acquire knowledge in new domains, we present an innovative generator structure called Domain Re-Modulation (DoRM) .

In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains acquire knowledge in new domains, we present an innovative generator structure called Domain Re-Modulation (DoRM) .

Mental health issues among college students have reached critical levels, significantly impacting academic performance and overall wellbeing. Predicting and understanding mental health status among college students is challenging due to three main factors: the necessity for large-scale longitudinal datasets, the prevalence of black-box machine learning models lacking transparency, and the tendency of existing approaches to provide aggregated insights at the population level rather than individualized understanding. To tackle these challenges, this paper presents I-HOPE, the first Interpretable Hierarchical mOdel for Personalized mEntal health prediction. I-HOPE is a two-stage hierarchical model, validated on the College Experience Study, the longest longitudinal mobile sensing dataset. This dataset spans five years and captures data from both pre-pandemic periods and the COVID-19 pandemic. I-HOPE connects raw behavioral features to mental health status through five defined behavioral categories as interaction labels. This approach achieves a prediction accuracy of 91%, significantly surpassing the 60-70% accuracy of baseline methods. In addition, our model distills complex patterns into interpretable and individualized insights, enabling the future development of tailored interventions and improving mental health support. The code is available at https://github.com/roycmeghna/I-HOPE.

We study a fair resource sharing problem, where a set of resources are to be shared among a group of agents. Each agent demands one resource and each resource can serve a limited number of agents. An agent cares about what resource they get as well as the externalities imposed by their mates, who share the same resource with them. Clearly, the strong notion of envy-freeness, where no agent envies another for their resource or mates, cannot always be achieved and we show that even deciding the existence of such a strongly envy-free assignment is an intractable problem. Hence, a more interesting question is whether (and in what situations) a relaxed notion of envy-freeness, the Pareto envyfreeness, can be achieved. Under this relaxed notion, an agent envies another only when they envy both the resource and the mates of the other agent. In particular, we are interested in a dorm assignment problem, where students are to be assigned to dorms with the same capacity and they have dichotomous preference over their dormmates. We show that when the capacity of each dorm is 2, a Pareto envy-free assignment always exists and we present a polynomial-time algorithm to compute such an assignment. Nevertheless, the result breaks immediately when the capacity increases to 3, in which case even Pareto envyfreeness cannot be guaranteed. In addition to the existential results, we also investigate the utility guarantees of (Pareto) envy-free assignments in our model.

Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms -- DORM, DORM+, and AdaHedgeD -- arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints can mitigate the regret penalty caused by delay. We pair this delay-as-optimism perspective with a new analysis of optimistic learning that exposes its robustness to hinting errors and a new meta-algorithm for learning effective hinting strategies in the presence of delay. We conclude by benchmarking our algorithms on four subseasonal climate forecasting tasks, demonstrating low regret relative to state-of-the-art forecasting models.

The last thing you want to do after spending hours staring at your laptop studying is spend more time staring at your laptop when you want to play a game or watch a movie. That's where game consoles come in. The Xbox One S starts at $244 on Amazon, while Microsoft regularly marks down the price of its entry-level system to around $200. In addition to being the place to play Halo and Gears of War, it's also an incredibly capable media machine thanks to its built-in UHD Blu-ray drive and support for HDR video. Plus, you might not have to spend any money on games for it: If you had a huge collection of digital games on the Xbox 360, Microsoft has made a swath of them playable on the One.

Twenty years ago, WIRED made a bold prediction: Cable modems are on the way out. "Things are looking bad for the cable industry: Careful study has shown that nearly the entire cable network would need to be replaced to make it suitable for two-way data traffic, and satellite services have been stealing away cable's television customers at an intolerable rate." Fast-forward to 2017 and ... cable modems are everywhere. Hey, points for journalistic confidence. Listen, predicting the future is thankless and hard and often ill-advised.

Chatbots are quickly becoming an integral part of an organization's customer experience strategy. Consumers love simple self-service and businesses love efficiency. But far too many businesses stop short of implementing chatbots because they fear the onboarding process. They believe that in order for a chatbot implementation to work correctly, it will need mountains of data and the staff will have to devote a ton of resources to training the technology on how best to respond to customers. As with many things, bigger does not always mean better when it comes to AI-fueled chatbot solutions.

Over the last couple of decades, those looking for a cluster management platform faced no shortage of choices. However, large-scale clusters are being asked to operate in different ways, namely by chewing on large-scale deep learning workloads--and this requires a specialized approach to get high utilization, efficiency, and performance. Nearly all of the cluster management tools from the high performance computing community are being bent in the machine learning direction, but for production deep learning shops, there appears to be a DIY tendency. This is not as complicated as it might sound, given the range of container-based open source tools, and such a homegrown approach can bake in tunings for specific frameworks and internal applications. The lack of a sufficiently robust cluster manager for a large-scale cluster handling large machine learning workloads pushed researchers at the Chinese machine learning giant, Sensetime, to build their own.

The robot, named Gaia, outside of a dorm on Harvard's campus. Would you let a stranger into your apartment building? Granting an unknown person access to a building was a humorous premise for a Seinfeld episode, but the decision to trust a stranger reveals insights into human psychology and touches on broader issues of trust in society. But what if, instead of a human, a robot knocked at your door? It's a question that Harvard University senior Serena Booth set out to answer with the help of a small, wheeled robot -- well, more like a roving nightstand -- that she stationed at the entrances to several dorms on campus.